© 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. 40346
    Prev
    Next
    INDEX
    Explanations

    Not natural language

    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
     z
    -0.31
    áz
    -0.31
     a
    -0.29
    ası
    -0.29
    tré
    -0.29
     а
    -0.27
    azz
    -0.27
     з
    -0.26
    iglia
    -0.26
     an
    -0.26
    POSITIVE LOGITS
     flats
    0.28
    jc
    0.26
    icon
    0.26
    .tw
    0.26
    ide
    0.25
    addons
    0.25
    ä¸ĩåIJ¨
    0.25
    itone
    0.25
     kontakte
    0.24
    .nd
    0.24
    Activations Density 6.901%

    No Known Activations