© 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. 42316
    Prev
    Next
    INDEX
    Explanations

    only

    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
     Most
    -0.60
    most
    -0.60
     most
    -0.59
    -most
    -0.54
    Most
    -0.54
     MOST
    -0.49
    _most
    -0.45
    æľĢ
    -0.41
    MOST
    -0.41
    æľĢéĩįè¦ģçļĦ
    -0.41
    POSITIVE LOGITS
     rather
    0.49
    rather
    0.38
    èĢĮéĿŀ
    0.37
    èĢĮä¸įæĺ¯
    0.35
     Rather
    0.35
     about
    0.33
     plutôt
    0.31
     so
    0.28
     remote
    0.28
    arness
    0.28
    Activations Density 0.003%

    No Known Activations