© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 8512
    Prev
    Next
    INDEX
    Explanations

    Is something generally safe?

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    얠
    -0.07
     transporting
    -0.07
    昨天
    -0.07
     ""),↵
    -0.07
    /boot
    -0.07
    HECK
    -0.07
    關於
    -0.07
    有助于
    -0.06
    AY
    -0.06
    是最
    -0.06
    POSITIVE LOGITS
    _ps
    0.08
    	des
    0.08
     sharedApplication
    0.08
    rical
    0.08
     phenomenal
    0.07
     modification
    0.07
    .routing
    0.07
    营销
    0.07
     nanoparticles
    0.07
     currentItem
    0.07
    Activations Density 0.101%

    No Known Activations