© 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. 6365
    Prev
    Next
    INDEX
    Explanations

    mosquitoes, bites, vectors

    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
    _POINTER
    -0.10
     доб
    -0.09
    é¢Ĺ
    -0.09
    çĴł
    -0.09
    为æĬĵæīĭ
    -0.09
    èį¦
    -0.09
    çļĦä¾ĭåŃIJ
    -0.08
    hire
    -0.08
    颢
    -0.08
    GetInstance
    -0.08
    POSITIVE LOGITS
    æĪIJ绩åįķ
    0.09
    åIJ»
    0.09
    ingly
    0.08
    åĪĩåħ¥
    0.08
    åѦåĪ°
    0.08
    айн
    0.08
    alchemy
    0.08
    åŃIJéĩĮ
    0.08
     Transcript
    0.08
     disasters
    0.08
    Activations Density 0.024%

    No Known Activations