© 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. 39419
    Prev
    Next
    INDEX
    Explanations

    http/https

    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
    mor
    -0.27
    íĤ·
    -0.26
    EGA
    -0.26
    cw
    -0.26
    tu
    -0.25
    tas
    -0.25
    xit
    -0.25
    usc
    -0.25
    yi
    -0.25
    ted
    -0.25
    POSITIVE LOGITS
    .reactivex
    0.27
    ?action
    0.27
    .ObjectMeta
    0.26
    legalArgumentException
    0.26
    \Routing
    0.26
    /sbin
    0.25
    \ActiveForm
    0.25
    /goto
    0.25
    .TryParse
    0.25
    \Framework
    0.24
    Activations Density 1.761%

    No Known Activations