© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 24415
    Prev
    Next
    INDEX
    Explanations

    long

    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
    ä¸įæĸŃæī©å¤§
    -0.28
    è´£
    -0.27
    tures
    -0.25
    çĽĨ
    -0.24
    ải
    -0.23
    èĬ±è´¹
    -0.23
    åħ±éĿĴåĽ¢
    -0.23
    âķ¢
    -0.23
    åħĥå®Ŀ
    -0.23
     brill
    -0.23
    POSITIVE LOGITS
    ç»ŃèĪª
    0.31
     dél
    0.29
    幡
    0.28
    long
    0.26
     punched
    0.26
    short
    0.25
    èĢģ乡
    0.25
    ç¢İçīĩ
    0.24
    Long
    0.24
     stayed
    0.24
    Activations Density 0.018%

    No Known Activations