© 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. 39502
    Prev
    Next
    INDEX
    Explanations

    ip

    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
    panel
    -0.30
     TIM
    -0.27
    TIM
    -0.27
    .har
    -0.27
     ashes
    -0.26
    Areas
    -0.26
     uncomfort
    -0.25
    ApiResponse
    -0.24
     PANEL
    -0.24
    peri
    -0.23
    POSITIVE LOGITS
    iece
    0.59
    ieces
    0.49
    iec
    0.39
    ill
    0.37
    icker
    0.35
    iek
    0.35
    ief
    0.33
     piece
    0.32
    iete
    0.31
    ilk
    0.31
    Activations Density 0.174%

    No Known Activations