© 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. 33323
    Prev
    Next
    INDEX
    Explanations

    full-length album, dropdown box

    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
    è£Ķ
    -0.10
    iant
    -0.08
    /device
    -0.08
    æŀ£
    -0.08
    Leod
    -0.08
    _CHIP
    -0.08
    åħ¥åı£
    -0.08
    ÑģÑĤой
    -0.08
    ink
    -0.08
    glass
    -0.08
    POSITIVE LOGITS
    ฯ
    0.16
    æŶéĹ´åĨħ
    0.09
    åį§
    0.09
    owi
    0.09
    äºĭçī©
    0.08
    çŀŃ解並
    0.08
    åį´æ²¡æľī
    0.08
    ðŁı¾
    0.08
    åĨľåľº
    0.08
    æīĢæľī人
    0.08
    Activations Density 0.647%

    No Known Activations