© 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. 9-TRANSCODER-HP
    7. 30021
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rega
    -0.26
    å±Ģéķ¿
    -0.26
    reeze
    -0.25
    ì¹ĺ
    -0.25
    avi
    -0.25
    bane
    -0.24
     itemprop
    -0.24
    pps
    -0.24
    æĦıåij³
    -0.24
    itched
    -0.23
    POSITIVE LOGITS
    e
    0.30
    è¿ĽåŁİ
    0.29
    .Arguments
    0.28
    igrated
    0.28
    论è¯ģ
    0.27
    uestion
    0.26
    _arguments
    0.26
    ep
    0.26
     argument
    0.26
    anse
    0.26
    Activations Density 10.224%

    No Known Activations