© 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. 5208
    Prev
    Next
    INDEX
    Explanations

    programming/technical issues

    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
    dana
    -0.28
    å¤ĩ
    -0.26
    phabet
    -0.26
    pent
    -0.26
    nock
    -0.26
     Sachs
    -0.25
    ohn
    -0.24
    roscope
    -0.24
    pond
    -0.24
     converge
    -0.24
    POSITIVE LOGITS
    annel
    0.26
    çijĻ
    0.25
     smoothly
    0.25
    ansen
    0.25
     hasNext
    0.24
     abandonment
    0.24
    release
    0.24
     apps
    0.24
    æŀī
    0.24
    èºIJ
    0.24
    Activations Density 0.055%

    No Known Activations