© 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. 31371
    Prev
    Next
    INDEX
    Explanations

    photovoltaics, modules, factor

    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
    åıijå¸ĥæŶéĹ´
    -0.10
     pier
    -0.09
    é«ĺ涨
    -0.09
    æĺ¥æĻļ
    -0.09
     Sinclair
    -0.09
    ä¸ĭæ²ī
    -0.09
    çħ§æĺİ
    -0.09
    å¾ĹçĽĬ
    -0.09
    为ä¸Ģä½ĵ
    -0.08
    磼
    -0.08
    POSITIVE LOGITS
    ANC
    0.09
    çĿĽ
    0.09
     Grip
    0.09
    太éĺ³èĥ½
    0.08
    åİ
    0.08
    æĻ´
    0.08
    _relationship
    0.08
    æķĻåѦ
    0.08
    éĩİå¿ĥ
    0.08
     sucker
    0.08
    Activations Density 0.043%

    No Known Activations