© 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. 40650
    Prev
    Next
    INDEX
    Explanations

    Binary or low values

    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
    ANCH
    -0.29
    CX
    -0.26
    æĺ¥æĻļ
    -0.25
    pressão
    -0.25
    çĽ
    -0.25
    agma
    -0.24
    mes
    -0.24
    ["+
    -0.24
    istry
    -0.24
    ervers
    -0.24
    POSITIVE LOGITS
     spur
    0.26
    ric
    0.25
     legit
    0.25
    æį®
    0.25
    serious
    0.24
    Ñħо
    0.24
    cce
    0.24
     asi
    0.24
     genuine
    0.23
    纯粹
    0.23
    Activations Density 0.928%

    No Known Activations