© 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. 7-RESID-POST-AA
    11. 41120
    Prev
    Next
    INDEX
    Explanations

    development environments

    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
    appings
    -0.08
     McGregor
    -0.08
     Train
    -0.08
    .cgColor
    -0.08
    .rb
    -0.07
    =#{
    -0.07
    monton
    -0.07
    แบร
    -0.07
    FragmentManager
    -0.07
    anny
    -0.07
    POSITIVE LOGITS
    *math
    0.07
     dissolution
    0.07
    .UInt
    0.07
     orb
    0.07
    .good
    0.07
     rebel
    0.06
     да
    0.06
     surveys
    0.06
    Пр
    0.06
    果
    0.06
    Activations Density 0.017%

    No Known Activations