© 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. 32-TRANSCODER-HP
    7. 43285
    Prev
    Next
    INDEX
    Explanations

    Complex math

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æģ¶æĢ§
    -0.28
    accom
    -0.27
    vard
    -0.27
    á¸į
    -0.26
    æłĩæĺİ
    -0.26
    èĮĤ
    -0.26
    -Man
    -0.25
    lot
    -0.25
    ãĥŃãĥ¼
    -0.24
    åºĦ
    -0.24
    POSITIVE LOGITS
    åĪĨéĶĢ
    0.28
    _PE
    0.27
    秦çļĩ
    0.27
    íķĦ
    0.27
    rules
    0.25
    åŃĺæ´»
    0.25
    éĥ½ä¸įæķ¢
    0.25
     distributions
    0.24
     Limits
    0.24
     distribution
    0.24
    Activations Density 0.026%

    No Known Activations