© 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. 40300
    Prev
    Next
    INDEX
    Explanations

    Expressing opinions

    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
    verity
    -0.29
    pare
    -0.29
    ãģĹãģ¾ãģĨ
    -0.27
    å³Ń
    -0.25
    æĬ¥
    -0.25
    å³»
    -0.24
    滩
    -0.24
    åĪĽæĸ°
    -0.24
    ız
    -0.24
    å¼Ģå¿ĥ
    -0.23
    POSITIVE LOGITS
    isphere
    0.27
    é¼·
    0.27
     asylum
    0.26
    <data
    0.26
    abic
    0.25
     <<<
    0.25
     vaguely
    0.24
     -----------------------------------------------------------------------------↵
    0.24
    inox
    0.24
    :Add
    0.24
    Activations Density 0.154%

    No Known Activations