© 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. 43234
    Prev
    Next
    INDEX
    Explanations

    important

    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
    主è¦ģ
    -0.30
    çļĦ主è¦ģ
    -0.28
    (keys
    -0.27
    éĩįè¦ģ
    -0.27
    bits
    -0.27
    еÑģÑģ
    -0.26
    éĩįçĤ¹é¡¹çĽ®
    -0.25
     Diss
    -0.25
     negatives
    -0.25
    主è¦ģçĶ¨äºİ
    -0.25
    POSITIVE LOGITS
     part
    0.71
     component
    0.54
     piece
    0.50
    éĥ¨åĪĨ
    0.46
     driver
    0.44
    _part
    0.42
    part
    0.40
    .part
    0.39
     Component
    0.38
    	part
    0.38
    Activations Density 0.010%

    No Known Activations