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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11-RESID-POST-AA
    6. 25906
    Prev
    Next
    INDEX
    Explanations

    mechanics, engineering

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Allows
    -0.08
     deduction
    -0.08
     Seventh
    -0.07
    Outside
    -0.07
     synonymous
    -0.07
     ?>"↵
    -0.07
    =node
    -0.07
    /new
    -0.07
     deductions
    -0.07
    这么说
    -0.07
    POSITIVE LOGITS
    .tr
    0.08
    ()->
    0.08
    .wr
    0.08
    股价
    0.07
    Insn
    0.07
    _Con
    0.07
    处置
    0.07
    婢
    0.07
     både
    0.07
    嵋
    0.07
    Activations Density 0.058%

    No Known Activations