© 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. 40930
    Prev
    Next
    INDEX
    Explanations

    Code, numbers, programming

    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
    inox
    -0.25
    aN
    -0.25
    romo
    -0.25
    çĤ¹åĩ»æŁ¥çľĭ
    -0.25
    alach
    -0.24
    AffineTransform
    -0.24
    ellow
    -0.24
     Chrom
    -0.24
    __).
    -0.24
    _ELEMENTS
    -0.24
    POSITIVE LOGITS
     deg
    0.28
    éĢĢ
    0.27
    shelf
    0.26
    Versions
    0.25
     dig
    0.24
     versión
    0.24
    _unique
    0.23
     versions
    0.23
    çļĦæĺ¯
    0.23
     deselect
    0.23
    Activations Density 0.091%

    No Known Activations