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. 19-RESID-POST-AA
    6. 71141
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     privilege
    -0.07
    全力以赴
    -0.07
     physique
    -0.07
    athon
    -0.07
    rem
    -0.07
    دة
    -0.07
     lectures
    -0.07
     gym
    -0.06
     born
    -0.06
    Immutable
    -0.06
    POSITIVE LOGITS
    名声
    0.07
    (dec
    0.07
    으면
    0.06
    新动能
    0.06
    =~
    0.06
    ราคา
    0.06
    ಗ
    0.06
    szą
    0.06
     pesos
    0.06
     samsung
    0.06
    Activations Density 0.011%

    No Known Activations