© 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. 39288
    Prev
    Next
    INDEX
    Explanations

    Code/errors/instructions

    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
    site
    -0.30
    imize
    -0.29
    山路
    -0.28
    shire
    -0.26
    Helvetica
    -0.26
    sei
    -0.26
    zi
    -0.25
    series
    -0.25
    ZN
    -0.25
    leanor
    -0.24
    POSITIVE LOGITS
     centroids
    0.31
     buds
    0.30
    ored
    0.29
    ended
    0.29
    AGED
    0.28
     redeemed
    0.28
     deductions
    0.28
    endon
    0.28
     endpoints
    0.27
     rods
    0.27
    Activations Density 4.450%

    No Known Activations