© 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. 10595
    Prev
    Next
    INDEX
    Explanations

    recommend to friend/family

    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
    eco
    -0.09
    åį¿
    -0.09
    è¿Ļ对äºİ
    -0.09
    aka
    -0.08
    (Pointer
    -0.08
    奴
    -0.08
    IPPING
    -0.08
    etre
    -0.08
    etri
    -0.07
    çĽĴåŃIJ
    -0.07
    POSITIVE LOGITS
    å¾Ĺèµ·
    0.11
    å¿ĥä¸ŃçļĦ
    0.09
    åIJĪåĩ»
    0.09
    亲åıĭ
    0.09
    olini
    0.09
    æľīä¿¡å¿ĥ
    0.09
    亲人
    0.09
    ëĶ°
    0.09
    渲
    0.09
    ä¼ļéĢīæĭ©
    0.09
    Activations Density 0.003%

    No Known Activations