© 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. 18892
    Prev
    Next
    INDEX
    Explanations

    dropped, dope, cold, peace, low, crushed

    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
    è¾ĺ
    -0.09
    çļĦåľ°æŃ¥
    -0.09
    纡
    -0.08
    妾
    -0.08
    ãģĦãģ¾ãģĻãģĮ
    -0.08
    åŃ£åIJİ
    -0.08
    é»İ
    -0.08
     oppos
    -0.08
    éĤ®è½®
    -0.08
     Mour
    -0.08
    POSITIVE LOGITS
    aal
    0.11
    uckets
    0.09
     Chill
    0.09
     Morton
    0.09
    å°ģ
    0.08
    éĴµ
    0.08
    .dispatch
    0.08
    ForKey
    0.08
    çĮĽ
    0.08
    èĤī
    0.08
    Activations Density 0.134%

    No Known Activations