© 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. 15-RESID-POST-AA
    11. 60237
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _vid
    -0.07
     concentrated
    -0.07
    柈
    -0.07
    	KEY
    -0.07
     UIAlert
    -0.07
     Computes
    -0.06
    weigh
    -0.06
    峭
    -0.06
    .It
    -0.06
    põe
    -0.06
    POSITIVE LOGITS
    说实
    0.08
    迷
    0.07
    ᶠ
    0.07
    していない
    0.07
    .Buffer
    0.07
    تباع
    0.07
    蝘
    0.07
    認識
    0.06
    ass
    0.06
    needed
    0.06
    Activations Density 0.068%

    No Known Activations