© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 83130
    Prev
    Next
    INDEX
    Explanations

    3

    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
     volley
    -0.07
    .jump
    -0.07
    끽
    -0.07
     konuştu
    -0.07
    겪
    -0.07
     Serge
    -0.07
    umping
    -0.07
    踊
    -0.06
    irthday
    -0.06
    Pg
    -0.06
    POSITIVE LOGITS
    _supported
    0.09
     wikipedia
    0.07
     تن
    0.06
    	ds
    0.06
     Products
    0.06
    ȍ
    0.06
    )obj
    0.06
    -runtime
    0.06
    ("`
    0.06
    WT
    0.06
    Activations Density 0.011%

    No Known Activations