© 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. 32-TRANSCODER-HP
    7. 42901
    Prev
    Next
    INDEX
    Explanations

    inter

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     preventing
    -0.27
    ately
    -0.25
     undis
    -0.25
    西路
    -0.25
    åĮ¹
    -0.24
    werk
    -0.24
     stopping
    -0.24
    .globalData
    -0.23
    erals
    -0.23
    ä¾Ŀçħ§
    -0.23
    POSITIVE LOGITS
    ference
    0.36
    ven
    0.33
     fer
    0.32
    ferences
    0.32
    fer
    0.32
    VEN
    0.32
    ÑĦеÑĢ
    0.31
    fp
    0.31
    Ven
    0.31
    venes
    0.30
    Activations Density 0.003%

    No Known Activations