© 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. 163511
    Prev
    Next
    INDEX
    Explanations

    (

    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
     split
    -0.32
    hel
    -0.29
     Builds
    -0.29
     definite
    -0.27
     con
    -0.27
     builds
    -0.26
     ped
    -0.26
     reg
    -0.26
     splits
    -0.25
     far
    -0.25
    POSITIVE LOGITS
    disposing
    0.27
     blaze
    0.26
    onga
    0.25
    signals
    0.25
    Tomorrow
    0.25
    大æĸ¹
    0.25
    Course
    0.24
    èµĥ
    0.24
    ä¿¡æģ¯æľįåĬ¡
    0.24
    kus
    0.24
    Activations Density 0.007%

    No Known Activations