© 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. 130289
    Prev
    Next
    INDEX
    Explanations

    forming new organizations

    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
    รส
    -0.28
    çݩ家们
    -0.28
     propagate
    -0.26
    pled
    -0.26
    .TXT
    -0.25
    ByExample
    -0.24
    erties
    -0.24
    .coll
    -0.24
    _REASON
    -0.23
    åĪijäºĭ责任
    -0.23
    POSITIVE LOGITS
    æIJŃ建
    0.36
    yp
    0.29
    ym
    0.27
     OS
    0.27
     Adam
    0.26
    éĿĴå¹´
    0.26
    .isNull
    0.26
    åĪĨå·¥
    0.26
    uki
    0.25
    空çĻ½
    0.25
    Activations Density 11.717%

    No Known Activations