© 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. 22-TRANSCODER-HP
    7. 98189
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åı¦ä¸Ģç§į
    -0.28
    èĥ½åĬĽåĴĮ
    -0.27
    åı¦ä¸Ģ
    -0.27
    .nr
    -0.25
    èĪ¬
    -0.25
    mont
    -0.25
    çłĶåĪ¤
    -0.24
     playground
    -0.24
    onds
    -0.23
    åı¦ä¸Ģ个
    -0.23
    POSITIVE LOGITS
    ä¹Łç®Ĺæĺ¯
    0.25
    æµĬ
    0.24
    _raise
    0.23
     tslib
    0.23
    éĺĸ
    0.23
    ÙĦÙħ
    0.23
    ubble
    0.23
    ç¾Ł
    0.23
    =#{
    0.22
    伦
    0.22
    Activations Density 0.008%

    No Known Activations