© 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. 48652
    Prev
    Next
    INDEX
    Explanations

    dark matter physics

    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
    erus
    -0.12
    oen
    -0.11
    æģģ
    -0.10
    åĽłæŀľ
    -0.10
    éªĭ
    -0.10
    Orientation
    -0.09
     ìłij
    -0.09
     Oliv
    -0.09
    åı£æ°Ķ
    -0.09
    ikk
    -0.09
    POSITIVE LOGITS
    ç«ĭæ³ķ
    0.09
    Instances
    0.09
    linger
    0.08
    åĭ¿
    0.08
    æĥľ
    0.08
    eps
    0.08
     REQ
    0.08
    å¾Ģå¹´
    0.08
    ç¢Ĺ
    0.08
    _missing
    0.08
    Activations Density 0.057%

    No Known Activations