© 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. 41209
    Prev
    Next
    INDEX
    Explanations

    cursor

    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
    plode
    -0.25
     Tribune
    -0.25
    lage
    -0.23
    çĵ´
    -0.23
    æī§
    -0.23
    ijľ
    -0.23
     spirits
    -0.23
    ertia
    -0.23
    Sac
    -0.23
     kin
    -0.23
    POSITIVE LOGITS
     curs
    0.98
     CUR
    0.93
     cursor
    0.90
     curse
    0.86
    åħī
    0.85
    cursor
    0.84
    	cursor
    0.83
     cur
    0.83
     Cursor
    0.81
    Cursor
    0.81
    Activations Density 0.015%

    No Known Activations