© 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. 14-TRANSCODER-HP
    7. 40175
    Prev
    Next
    INDEX
    Explanations

    Code/Documents/Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amat
    -0.28
    åĪĨéħį
    -0.28
    vey
    -0.27
    groupName
    -0.27
     sill
    -0.26
    sweet
    -0.26
    çĮ¿
    -0.26
    getManager
    -0.26
    ewhat
    -0.26
    笥
    -0.26
    POSITIVE LOGITS
    ç¾¹
    0.28
    incipal
    0.26
    æĿ¥ä¸įåıĬ
    0.26
     Thi
    0.26
     Tig
    0.25
    ASK
    0.25
    Endpoints
    0.25
     shame
    0.24
    gui
    0.24
    ÑĪка
    0.24
    Activations Density 0.981%

    No Known Activations