© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35787
    Prev
    Next
    INDEX
    Explanations

    may be, might be, little bit

    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
    bis
    -0.10
    åıĭè°Ĭ
    -0.10
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.10
    欢è¿İ
    -0.10
    éĢŀ
    -0.09
    个åĪ«
    -0.09
    主ä¸ļ
    -0.09
    欢è¿İæĤ¨
    -0.09
    éĿłè°±
    -0.09
    ç±³åħ°
    -0.09
    POSITIVE LOGITS
    è¶ħåĩº
    0.09
    ä¸įçķĻ
    0.09
     butter
    0.08
    è¾ľè´Ł
    0.08
    çĤ¼
    0.08
     Reflex
    0.08
     Larry
    0.08
    Enumerator
    0.08
    .hd
    0.08
    è¯İ
    0.08
    Activations Density 0.163%

    No Known Activations