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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39000
    Prev
    Next
    INDEX
    Explanations

    New

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edException
    -0.31
    éħŀ
    -0.27
     ApiException
    -0.27
    _ALWAYS
    -0.26
     fundra
    -0.26
     infra
    -0.25
    FilterWhere
    -0.25
     TestUtils
    -0.25
    ç»ĻåĪ«äºº
    -0.25
     EXCEPTION
    -0.24
    POSITIVE LOGITS
    de
    0.33
    cause
    0.32
     H
    0.32
    n
    0.31
    ent
    0.30
    h
    0.30
    cas
    0.30
     Lo
    0.29
    end
    0.28
    position
    0.28
    Activations Density 0.347%

    No Known Activations