© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 12775
    Prev
    Next
    INDEX
    Explanations

    cancer radiation therapy

    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_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
     вес
    -0.07
     precip
    -0.07
    ROP
    -0.07
     COD
    -0.07
     tap
    -0.07
    reports
    -0.07
    .asList
    -0.07
    致使
    -0.06
     mare
    -0.06
    出台了
    -0.06
    POSITIVE LOGITS
    왤
    0.08
    tcp
    0.07
     SSL
    0.07
    球迷
    0.07
    ensible
    0.07
    等人
    0.07
    £o
    0.07
     Kabul
    0.07
     Bool
    0.07
    ível
    0.07
    Activations Density 0.026%

    No Known Activations