© 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. 33-TRANSCODER-HP
    7. 53650
    Prev
    Next
    INDEX
    Explanations

    eating, food

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parable
    -0.32
    åħ·
    -0.30
    R
    -0.29
    æĪIJ
    -0.28
    æĪĺ
    -0.27
    æĻ®
    -0.27
    å¯ĵ
    -0.27
    adratic
    -0.26
    ä¿¡
    -0.26
    ometric
    -0.26
    POSITIVE LOGITS
    OfString
    0.30
    uling
    0.28
    änd
    0.27
    å¿»
    0.26
     rin
    0.26
     DEAL
    0.26
    /cop
    0.26
     Dealer
    0.26
    GetString
    0.25
    å¾Īæĸ¹ä¾¿
    0.25
    Activations Density 0.022%

    No Known Activations