© 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. 11-RESID-POST-AA
    11. 107886
    Prev
    Next
    INDEX
    Explanations

    floods

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     float
    -0.07
     allows
    -0.07
    𨐈
    -0.06
    initely
    -0.06
     ring
    -0.06
    舉辦
    -0.06
    +:
    -0.06
     specify
    -0.06
    ﺫ
    -0.06
    	sys
    -0.06
    POSITIVE LOGITS
     Mobil
    0.09
    (student
    0.09
    )new
    0.08
    (mapStateToProps
    0.07
    ilik
    0.07
     Dawson
    0.07
    演讲
    0.07
    党和政府
    0.07
    employ
    0.07
    boro
    0.07
    Activations Density 0.020%

    No Known Activations