Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 10764
    Prev
    Next
    INDEX
    Explanations

    Brown

    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
    8
    -0.07
    Keith
    -0.07
     Eighth
    -0.07
    キ
    -0.07
    (Network
    -0.07
     pubkey
    -0.07
    ἥ
    -0.07
     cue
    -0.07
    🎋
    -0.07
     Outreach
    -0.07
    POSITIVE LOGITS
     Brown
    0.09
    表述
    0.07
     a
    0.07
    자가
    0.06
    _pag
    0.06
     and
    0.06
    明
    0.06
     bloque
    0.06
    .evaluate
    0.06
     redund
    0.06
    Activations Density 0.010%

    No Known Activations