© 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. 163371
    Prev
    Next
    INDEX
    Explanations

    from

    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
    лей
    -0.29
    Properties
    -0.26
    ÑĥÑī
    -0.25
    çļĦç¾İ好
    -0.25
    åıĪæĺ¯
    -0.25
    åĪĨå±Ģ
    -0.25
     busiest
    -0.24
    è¿Ļæł·ä¸Ģ个
    -0.24
     Properties
    -0.24
    çļĦåĽŀçŃĶ
    -0.24
    POSITIVE LOGITS
    çIJĨæĢ§
    0.28
     vard
    0.25
    abble
    0.25
     ashes
    0.24
    AXB
    0.24
    (mask
    0.24
    /=
    0.24
     grow
    0.24
    idding
    0.23
    fold
    0.23
    Activations Density 0.004%

    No Known Activations