© 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. 18-TRANSCODER-HP
    7. 89594
    Prev
    Next
    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Click
    -0.29
     Idea
    -0.28
    ç«ĭåľº
    -0.26
     Kro
    -0.25
    Click
    -0.25
    éģ·
    -0.25
    涨
    -0.24
    èݽ
    -0.24
    thumbs
    -0.24
    æĢģ度
    -0.24
    POSITIVE LOGITS
    atel
    0.27
    omm
    0.26
    imson
    0.26
    fällt
    0.25
    =sc
    0.25
    åIJ¦åĪĻ
    0.25
    ietf
    0.25
    .Generation
    0.25
    æķ£
    0.24
     trail
    0.23
    Activations Density 12.333%

    No Known Activations