© 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. 41991
    Prev
    Next
    INDEX
    Explanations

    fundamental

    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
    ainen
    -0.27
    azu
    -0.27
    主è¦ģ
    -0.26
    éŃĶ鬼
    -0.26
    (key
    -0.24
    cox
    -0.24
    uld
    -0.24
     main
    -0.24
    zell
    -0.24
    âu
    -0.24
    POSITIVE LOGITS
    ness
    0.38
    ly
    0.33
     working
    0.30
     aspects
    0.30
     parts
    0.29
     pieces
    0.29
     act
    0.29
     ten
    0.29
     driving
    0.29
    оÑģÑĤÑĮ
    0.28
    Activations Density 0.004%

    No Known Activations