© 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. 50040
    Prev
    Next
    INDEX
    Explanations

    Japanese characters followed by English words

    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
     ÑįÑĤап
    -0.09
    ophil
    -0.09
    衽
    -0.09
    olas
    -0.09
    ä¸Ģç¬Ķ
    -0.08
    ergy
    -0.08
    ä½³
    -0.08
    leÅŁ
    -0.08
    audit
    -0.08
    ä½ıåľ¨
    -0.08
    POSITIVE LOGITS
    èĢĥè¯ģ
    0.09
    سط
    0.09
    éĵ¶æ²³
    0.09
    ngine
    0.08
    IMS
    0.08
    è¯Ĥ
    0.08
    æĭľå¸Ī
    0.08
    archical
    0.08
    åĽŀ头çľĭ
    0.08
    èªĵ
    0.08
    Activations Density 0.002%

    No Known Activations