© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4891
    Prev
    Next
    INDEX
    Explanations

    Web page content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iless
    -0.29
    è¦ģ好好
    -0.25
     deterministic
    -0.24
    梵
    -0.24
     intimate
    -0.24
    ãĤ¶
    -0.24
    åĴ¨è¯¢æľįåĬ¡
    -0.23
    /info
    -0.23
     abused
    -0.23
    çīĪæĿĥæīĢæľī
    -0.23
    POSITIVE LOGITS
    å¹´éĻIJ
    0.27
    ex
    0.26
    èĢĮæĪIJ
    0.25
    ünde
    0.24
    åĭŁ
    0.24
     Mines
    0.24
    èĦĤ
    0.24
    åĩ¼
    0.24
    esar
    0.23
    _hooks
    0.23
    Activations Density 0.033%

    No Known Activations