© 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. 23-TRANSCODER-HP
    7. 24481
    Prev
    Next
    INDEX
    Explanations

    technical/formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raised
    -0.28
    @Resource
    -0.26
    æĹ¥åľ¨
    -0.25
     fixtures
    -0.25
    -plan
    -0.25
     Written
    -0.25
    boro
    -0.25
     Fixture
    -0.24
    å¾Īå¥½åľ°
    -0.24
    $tpl
    -0.24
    POSITIVE LOGITS
    è¿ĻåIJį
    0.26
    _PRESENT
    0.25
    æĬ¥
    0.25
    l
    0.25
    åħĪçĶŁ
    0.25
    å·¥ä½ľæĢ»ç»ĵ
    0.25
    æīĵ
    0.24
    irect
    0.24
    uby
    0.24
    æ±ĩæĬ¥
    0.24
    Activations Density 0.001%

    No Known Activations