© 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. 20-TRANSCODER-HP
    7. 108211
    Prev
    Next
    INDEX
    Explanations

    Computer actions/commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     persönlich
    -0.27
    misc
    -0.26
    çªĺ
    -0.25
    åĽłä¸ºå®ĥ
    -0.25
    åħĪè¡Į
    -0.24
    ResponseType
    -0.24
    æĬĬ她
    -0.24
    åijĬè¯ī她
    -0.23
    dÃŃ
    -0.23
     VAN
    -0.23
    POSITIVE LOGITS
    olutely
    0.28
     rig
    0.26
    éģ²
    0.26
    æ³ķå®ļ
    0.25
    optimized
    0.25
    uye
    0.24
     Builds
    0.24
    å½±
    0.24
    onto
    0.24
    ilst
    0.23
    Activations Density 2.992%

    No Known Activations