© 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. 5248
    Prev
    Next
    INDEX
    Explanations

    Dates

    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
    èĤ¼
    -0.30
    [--
    -0.26
     postfix
    -0.26
     Phi
    -0.25
    ä¹Łåıªæľī
    -0.25
     PHI
    -0.25
    /person
    -0.25
     mentally
    -0.25
    失æķĪ
    -0.24
    çŁ¥å·±
    -0.24
    POSITIVE LOGITS
     Blues
    0.28
    èµĭ
    0.27
     pys
    0.27
    红åĪ©
    0.27
     vis
    0.27
     gj
    0.27
    大åıij
    0.26
     Sta
    0.25
    产
    0.25
    符
    0.25
    Activations Density 0.048%

    No Known Activations