© 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. 40843
    Prev
    Next
    INDEX
    Explanations

    to

    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
     Affero
    -0.34
    CCI
    -0.26
    侧éĿ¢
    -0.26
    gee
    -0.24
    æĸ°åŁİ
    -0.24
    ãĤŃãĥ£
    -0.24
    serter
    -0.24
     spots
    -0.24
     esl
    -0.24
    =end
    -0.23
    POSITIVE LOGITS
    产éĩı
    0.29
    aud
    0.28
    åĪĴåĪĨ
    0.27
    otation
    0.25
    ienne
    0.25
    wand
    0.25
    .Multiline
    0.24
    )application
    0.24
    eni
    0.24
    python
    0.24
    Activations Density 0.514%

    No Known Activations