© 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. 65366
    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
     people
    -0.08
    @api
    -0.07
     understand
    -0.07
    حصر
    -0.07
    提现
    -0.07
    牦
    -0.07
    设计理念
    -0.07
    🧊
    -0.06
    tf
    -0.06
     IAM
    -0.06
    POSITIVE LOGITS
    Bool
    0.07
    _methods
    0.07
     Bun
    0.07
    ping
    0.07
     Motor
    0.07
    คอ
    0.07
    	connect
    0.06
     BOOL
    0.06
    _err
    0.06
    ন
    0.06
    Activations Density 0.014%

    No Known Activations