© 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. 23-TRANSCODER-HP
    7. 162385
    Prev
    Next
    INDEX
    Explanations

    cysts, polyps, medical conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    té
    -0.29
    antee
    -0.28
    sense
    -0.28
     themselves
    -0.27
    pins
    -0.27
    sol
    -0.26
    åħ¼
    -0.25
    ippets
    -0.25
    irse
    -0.25
    溶
    -0.25
    POSITIVE LOGITS
     éĶ
    0.28
     Sinclair
    0.28
     larg
    0.28
     need
    0.28
    çŃ²
    0.24
    Ñıз
    0.24
    æĨĭ
    0.24
     khợi
    0.24
    è¹Ĭ
    0.23
     rug
    0.23
    Activations Density 0.007%

    No Known Activations