© 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. 5975
    Prev
    Next
    INDEX
    Explanations

    Coalition, Consortium, consensus

    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
    éĢĤå½ĵçļĦ
    -0.28
    èĢģå¸ĪçļĦ
    -0.25
    å¿Į
    -0.24
    ording
    -0.24
    ippers
    -0.23
    éĮ¢
    -0.23
     Anthem
    -0.23
     cid
    -0.23
    eren
    -0.23
    åİ¿åŁİ
    -0.23
    POSITIVE LOGITS
    èĢĮæĪIJ
    0.25
    åģļå¾Ĺ
    0.24
    建设åĴĮ
    0.23
    xAF
    0.23
    们
    0.23
    æł¹æį®èĩªå·±
    0.23
    ntity
    0.22
    -wide
    0.22
    iplinary
    0.22
    åŃIJéĩĮ
    0.22
    Activations Density 2.053%

    No Known Activations