© 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. 39376
    Prev
    Next
    INDEX
    Explanations

    technical/legal texts

    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
    .inputs
    -0.27
    ITIONS
    -0.27
     ramps
    -0.26
    åıĤåĬłä¼ļè®®
    -0.26
    asions
    -0.25
    åį´è¢«
    -0.24
    HG
    -0.24
    'Ãł
    -0.24
     afterward
    -0.24
    hints
    -0.23
    POSITIVE LOGITS
    a
    0.33
    olo
    0.29
    id
    0.29
    dden
    0.28
    ocus
    0.28
    а
    0.28
    insky
    0.28
    eled
    0.28
    ified
    0.27
     void
    0.27
    Activations Density 0.020%

    No Known Activations