© 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. 41512
    Prev
    Next
    INDEX
    Explanations

    code/text snippets

    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
    ifest
    -0.31
    éļĶ
    -0.27
     Fre
    -0.26
    ará
    -0.25
    +_
    -0.25
    æļĿ
    -0.25
    æīij
    -0.25
     Oriental
    -0.24
    adin
    -0.24
    ä½ĺ
    -0.24
    POSITIVE LOGITS
     would
    1.21
    would
    1.11
     Would
    1.08
    Would
    0.99
     wouldn
    0.72
     serait
    0.70
     zou
    0.69
     serÃŃa
    0.68
     würde
    0.66
     Wouldn
    0.66
    Activations Density 0.000%

    No Known Activations