© 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. 31-TRANSCODER-HP
    7. 18913
    Prev
    Next
    INDEX
    Explanations

    Food, recipes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IClient
    -0.26
    stück
    -0.26
    绣
    -0.26
    ä¸Ģçĵ¶
    -0.25
     Stand
    -0.25
     Mich
    -0.25
    emet
    -0.25
    ä¸ĭ车
    -0.24
     Carlson
    -0.24
    jon
    -0.24
    POSITIVE LOGITS
    赫
    0.29
     ÑħозÑıй
    0.28
     PIL
    0.26
    à¹Ģà¸Ĺศ
    0.26
    fresh
    0.25
     mediums
    0.25
    èĪĪ
    0.25
     Holidays
    0.25
    hits
    0.25
    åıijçĥ§
    0.25
    Activations Density 0.963%

    No Known Activations