© 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
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5212
    Prev
    Next
    INDEX
    Explanations

    and/or

    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
    IBUT
    -0.27
    å·²ä¹ħ
    -0.27
    plug
    -0.26
    anja
    -0.25
    uptools
    -0.24
    å·²ä¹ħçļĦ
    -0.24
    wap
    -0.24
    ãģĹãģŁãģĵãģ¨
    -0.24
    oot
    -0.24
    æŶéĹ´åĴĮ
    -0.24
    POSITIVE LOGITS
    shit
    0.31
    çļĦéĤ£ç§į
    0.28
    ä¸įæĿ¥
    0.27
     Mor
    0.27
    è´µ
    0.27
    è¿·
    0.25
    管çIJĨä¸Ńå¿ĥ
    0.24
    Mor
    0.24
    -Con
    0.24
    ections
    0.24
    Activations Density 0.496%

    No Known Activations