© 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. 5947
    Prev
    Next
    INDEX
    Explanations

    Mixed, diverse and unstructured information

    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
     sn
    -0.30
    ÃŃch
    -0.28
    -sn
    -0.28
    çļĦåIJĮæŶ
    -0.27
    iously
    -0.27
    CEL
    -0.26
    /sn
    -0.26
    _FE
    -0.26
     cul
    -0.25
    屬
    -0.25
    POSITIVE LOGITS
    anca
    0.31
    ertainment
    0.27
    beeld
    0.24
    acier
    0.24
    为äºĨ让
    0.23
    ĮĢ
    0.23
    fi
    0.23
     Nordic
    0.23
    åı¦è¡Į
    0.23
     Auto
    0.23
    Activations Density 0.015%

    No Known Activations