© 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. 43178
    Prev
    Next
    INDEX
    Explanations

    contains "at"

    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
    è¦ģ好好
    -0.24
    bic
    -0.24
    èĶĵ
    -0.23
    åĩ¡
    -0.23
    zon
    -0.22
    iou
    -0.22
    ande
    -0.22
    è¿Ļåĩłå¤©
    -0.22
    éģįåıĬ
    -0.22
    wort
    -0.22
    POSITIVE LOGITS
     at
    1.69
     tại
    1.13
    _at
    1.10
    At
    1.09
     At
    1.07
    	at
    1.06
    .at
    1.05
    -at
    0.92
    at
    0.84
     Tại
    0.77
    Activations Density 0.002%

    No Known Activations