© 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. 39717
    Prev
    Next
    INDEX
    Explanations

    d

    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
    ghan
    -0.29
    åĽłä¸ºæĪij们
    -0.28
    ctica
    -0.27
    Di
    -0.26
    ç©¿
    -0.25
     di
    -0.25
    åıĪ被
    -0.25
    åıĪ好
    -0.25
     suk
    -0.24
     sucker
    -0.24
    POSITIVE LOGITS
    op
    0.32
    expr
    0.30
    express
    0.28
    ynth
    0.28
    -expression
    0.27
     expr
    0.27
    expression
    0.26
    (expr
    0.26
    表达
    0.25
     express
    0.24
    Activations Density 6.810%

    No Known Activations