© 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. 19-RESID-POST-AA
    6. 68730
    Prev
    Next
    INDEX
    Explanations

    Sports winning/losing streaks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .micro
    -0.08
    .firstName
    -0.07
    劝
    -0.07
    Which
    -0.07
     한번
    -0.07
     Advanced
    -0.07
    Western
    -0.07
    罾
    -0.07
    萬
    -0.07
     cặp
    -0.07
    POSITIVE LOGITS
    )){↵
    0.07
     DIS
    0.07
     confess
    0.07
    seealso
    0.06
     revelations
    0.06
     fittings
    0.06
    Expressions
    0.06
     Ger
    0.06
    `)↵
    0.06
    摅
    0.06
    Activations Density 0.041%

    No Known Activations