© 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. 40905
    Prev
    Next
    INDEX
    Explanations

    where

    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
    åijĥ
    -0.28
    ulator
    -0.27
    flare
    -0.25
    ÑĢог
    -0.25
    RowCount
    -0.25
    ullah
    -0.24
    æĸĩä½ĵ
    -0.24
    nea
    -0.24
    _-_
    -0.24
     anus
    -0.23
    POSITIVE LOGITS
     mang
    0.27
    adge
    0.27
     LANGUAGE
    0.24
    моÑĤ
    0.24
    ":""
    0.24
    ellation
    0.24
    çĿ¬
    0.23
    ¢åįķ
    0.23
    IFO
    0.23
    çģŀ
    0.23
    Activations Density 1.264%

    No Known Activations