© 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. 41610
    Prev
    Next
    INDEX
    Explanations

    a

    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
    Clone
    -0.60
     Copy
    -0.60
     Clone
    -0.59
    clone
    -0.58
     cloning
    -0.57
     clone
    -0.57
    .Clone
    -0.57
     copy
    -0.55
     copying
    -0.54
     clones
    -0.54
    POSITIVE LOGITS
    -c
    0.46
    -C
    0.33
    _c
    0.31
     coc
    0.31
     к
    0.30
    oc
    0.29
    	C
    0.28
     cosy
    0.28
    pp
    0.27
    "C
    0.27
    Activations Density 0.020%

    No Known Activations