© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21901
    Prev
    Next
    INDEX
    Explanations

    days

    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
    ship
    -0.10
    åħ¶æīĢ
    -0.09
    oled
    -0.09
    ger
    -0.08
     dual
    -0.08
    avn
    -0.08
    åĩºå¸Ń
    -0.08
    ÑģÑĮ
    -0.08
     Lifecycle
    -0.08
    å´´
    -0.08
    POSITIVE LOGITS
    è¯Ŀ说
    0.10
    ä¸Ģæĸ¹éĿ¢æĺ¯
    0.09
    days
    0.09
    åĻľ
    0.09
    ucker
    0.09
    åŃIJéĩĮ
    0.09
    éķ¿çŁŃ
    0.08
    çĽ¸ä¼ł
    0.08
    .sz
    0.08
    Days
    0.08
    Activations Density 0.034%

    No Known Activations