© 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. 42915
    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
    èĢĮä¸įæĺ¯
    -0.43
    èĢĮéĿŀ
    -0.43
     rather
    -0.41
    rather
    -0.39
     Rather
    -0.36
    Rather
    -0.35
    uspend
    -0.28
     plutôt
    -0.28
    太
    -0.27
     too
    -0.27
    POSITIVE LOGITS
    ä½ľä¸º
    0.37
    ä½ľä¸ºä¸Ģ个
    0.34
     as
    0.33
    ä½ľçĤº
    0.32
     Back
    0.30
     back
    0.30
     emb
    0.29
    leta
    0.28
    -back
    0.27
    ä½ľ
    0.27
    Activations Density 0.006%

    No Known Activations