© 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. 41803
    Prev
    Next
    INDEX
    Explanations

    Chemical elements/compounds

    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
     cell
    -0.49
     Cell
    -0.47
    Cell
    -0.45
    cell
    -0.45
    _cell
    -0.43
    -cell
    -0.41
    ç»Ĩèĥŀ
    -0.41
    	cell
    -0.40
     cells
    -0.38
     cellular
    -0.38
    POSITIVE LOGITS
    æ°§
    0.33
     hap
    0.28
    _OC
    0.28
    genic
    0.28
    åŁºåĽł
    0.27
     gen
    0.26
    (:,:,
    0.26
    çĶµéĩı
    0.26
     Oxygen
    0.26
     oxygen
    0.25
    Activations Density 0.013%

    No Known Activations