© 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. 12-TRANSCODER-HP
    7. 22871
    Prev
    Next
    INDEX
    Explanations

    Research, code, legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å®ŀéĻħæݧåĪ¶
    -0.26
    ucker
    -0.25
    ä¸Ģè§Ĵ
    -0.25
    ç³Ł
    -0.25
    éĢĴ
    -0.25
    å°±æĺ¯è¿Ļæł·
    -0.25
    æľĽçĿĢ
    -0.24
     Credits
    -0.24
    代表
    -0.23
    unwrap
    -0.23
    POSITIVE LOGITS
    ayout
    0.29
    ±Ð¾ÑĤ
    0.25
    .et
    0.25
     IDF
    0.25
     canceled
    0.25
    rng
    0.25
    riba
    0.24
    edic
    0.24
    spinner
    0.24
    lex
    0.24
    Activations Density 0.000%

    No Known Activations