© 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. 41254
    Prev
    Next
    INDEX
    Explanations

    Technical and abstract writing

    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
    reo
    -0.27
    veillance
    -0.27
     suf
    -0.27
     Held
    -0.26
    igi
    -0.26
    ãĥį
    -0.25
    åİŁåĽłæĺ¯
    -0.25
    ино
    -0.24
    ins
    -0.24
     fasc
    -0.24
    POSITIVE LOGITS
     Punch
    0.31
    纸ä¸Ĭ
    0.30
    岬
    0.29
    atypes
    0.27
    unate
    0.27
    ató
    0.26
    åĨĻåŃĹ
    0.26
    æijĶ
    0.25
    åıįè¿ĩæĿ¥
    0.25
    (arguments
    0.25
    Activations Density 0.959%

    No Known Activations