© 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. 41883
    Prev
    Next
    INDEX
    Explanations

    is

    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
     rather
    -0.44
    èĢĮéĿŀ
    -0.43
    rather
    -0.42
    èĢĮä¸įæĺ¯
    -0.40
     plutôt
    -0.39
     Rather
    -0.37
    Rather
    -0.36
    edException
    -0.34
    ãģ§ãģ¯ãģªãģı
    -0.29
    WITHOUT
    -0.28
    POSITIVE LOGITS
     by
    0.42
     as
    0.35
     By
    0.35
    çĶ±
    0.34
    By
    0.34
    _BY
    0.33
    _by
    0.32
    çĶ±ä¸ŃåĽ½
    0.32
    ä½ľä¸º
    0.32
    (By
    0.31
    Activations Density 0.002%

    No Known Activations