© 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. 54459
    Prev
    Next
    INDEX
    Explanations

    free of charge

    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
    usher
    -0.09
    æªIJ
    -0.08
     crowd
    -0.08
    æĽ´éĩįè¦ģ
    -0.08
    å¾Īéĩįè¦ģçļĦ
    -0.08
    reeze
    -0.08
    foon
    -0.08
    _INSTANCE
    -0.08
    .ga
    -0.08
     crowds
    -0.08
    POSITIVE LOGITS
    .nd
    0.09
     оÑĤд
    0.09
    éĥ½èĥ½
    0.09
    çĶµéĩı
    0.09
    LY
    0.08
    IGINAL
    0.08
    çģ«åĬĽ
    0.08
    åıijå±ķæł¼å±Ģ
    0.08
    注åĨĮèµĦæľ¬
    0.08
    oned
    0.08
    Activations Density 0.013%

    No Known Activations