© 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. 33-TRANSCODER-HP
    7. 53755
    Prev
    Next
    INDEX
    Explanations

    say "you"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     us
    -1.43
    us
    -1.16
     Us
    -1.10
    	us
    -1.02
    -us
    -1.02
    Us
    -1.01
    _us
    -0.96
    (us
    -0.95
    .us
    -0.90
     наÑģ
    -0.76
    POSITIVE LOGITS
     we
    0.97
    we
    0.95
     We
    0.93
    We
    0.91
     мÑĭ
    0.90
    _we
    0.76
    .we
    0.76
    -we
    0.75
    æĪij们
    0.74
    WE
    0.68
    Activations Density 0.193%

    No Known Activations