© 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. 22528
    Prev
    Next
    INDEX
    Explanations

    tag archives

    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
    åĬ¡
    -0.09
    ç«Ļéķ¿
    -0.08
    ä¸įæĸŃåľ°
    -0.08
    edics
    -0.08
    Ordinal
    -0.08
    åħ¨çľģ
    -0.08
    建åħļ
    -0.08
    管家
    -0.08
    åĮºç®¡å§Ķä¼ļ
    -0.07
     Forums
    -0.07
    POSITIVE LOGITS
    opr
    0.10
    зÑĥ
    0.10
    ongyang
    0.09
    éķ¿çĽ¸
    0.08
    reich
    0.08
    pios
    0.08
    åİļåİļçļĦ
    0.08
    peria
    0.08
    以便
    0.08
     Abel
    0.08
    Activations Density 0.204%

    No Known Activations