© 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. 40246
    Prev
    Next
    INDEX
    Explanations

    Veget

    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
     mercenaries
    -0.32
    .transforms
    -0.27
     girlfriends
    -0.27
     humili
    -0.26
    篪
    -0.26
    å©ļåIJİ
    -0.26
     disclaimer
    -0.25
    .UseVisualStyleBackColor
    -0.25
     disgu
    -0.25
    è®°å¿ĨåĬĽ
    -0.25
    POSITIVE LOGITS
    atal
    0.40
    ational
    0.40
    ation
    0.37
    at
    0.33
     Ion
    0.33
    otal
    0.32
    ting
    0.31
    rade
    0.31
    als
    0.31
    alth
    0.31
    Activations Density 0.765%

    No Known Activations