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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RESID-POST-AA
    11. 103106
    Prev
    Next
    INDEX
    Explanations

    profiling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _MOVE
    -0.08
     manage
    -0.07
    𝙮
    -0.07
     Witch
    -0.07
    weekly
    -0.06
     invitation
    -0.06
    첮
    -0.06
     язык
    -0.06
    .Free
    -0.06
    .isTrue
    -0.06
    POSITIVE LOGITS
     Xen
    0.08
    arel
    0.07
    很好地
    0.07
    特定
    0.07
    model
    0.07
     harm
    0.07
    多种形式
    0.07
     нагруз
    0.07
    azer
    0.07
     дав
    0.07
    Activations Density 0.013%

    No Known Activations