© 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. 32-TRANSCODER-HP
    7. 42117
    Prev
    Next
    INDEX
    Explanations

    ABC

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idebar
    -0.26
    ourd
    -0.24
    vae
    -0.24
    /rem
    -0.24
     trop
    -0.24
    WithTitle
    -0.24
     евÑĢ
    -0.23
     deb
    -0.23
     pass
    -0.23
     finale
    -0.23
    POSITIVE LOGITS
    纤
    0.26
    -cl
    0.26
    æĭĪ
    0.26
    *A
    0.24
    adder
    0.24
    ç²¾éĢļ
    0.24
    asley
    0.24
    PN
    0.24
    cam
    0.23
     Capacity
    0.23
    Activations Density 0.002%

    No Known Activations