© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26607
    Prev
    Next
    INDEX
    Explanations

    UNITED STATES of America v

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flatt
    -0.09
    åı¸é©¬
    -0.09
    CORD
    -0.09
    _GRANTED
    -0.08
    çĻ½å¤©
    -0.08
    çł´
    -0.08
    æĺ¥å¤ı
    -0.08
    æĭ³
    -0.08
     Pil
    -0.08
     nit
    -0.08
    POSITIVE LOGITS
    åĽ¿
    0.10
    æ·¡åĮĸ
    0.09
     Omn
    0.09
    æİī
    0.09
    IRC
    0.08
    ä¸Ģ群
    0.08
    第ä¸ī人
    0.08
    ä¸Ģ大åłĨ
    0.08
    å¥ģ
    0.08
    渼
    0.08
    Activations Density 0.887%

    No Known Activations