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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-4B
    3. 19-TRANSCODER-HP
    4. 5850
    Prev
    Next
    INDEX
    Explanations

    Superlatives

    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
     æĸ
    -0.28
    两åıª
    -0.27
    Ñĥни
    -0.27
    éĵ
    -0.27
    bull
    -0.26
     respective
    -0.26
    xon
    -0.25
    //(
    -0.25
    éĢļ常æĺ¯
    -0.25
     stacks
    -0.24
    POSITIVE LOGITS
    ä¸Ģç§Ĵ
    0.29
    ãĤĴåıĸãĤĬ
    0.27
    eil
    0.25
    åĪĹ为
    0.24
    ä¸Ģçľ¼
    0.24
    rug
    0.24
    _critical
    0.24
    ä¸Ģå¹´
    0.24
    館
    0.23
     tough
    0.23
    Activations Density 0.013%

    No Known Activations