© 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. 30582
    Prev
    Next
    INDEX
    Explanations

    interest to / relevant to

    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
    issy
    -0.09
    为æ°ij
    -0.09
     lược
    -0.09
    apel
    -0.08
    å°±æĺ¯ä¸Ģ个
    -0.08
    è¡Ģèħ¥
    -0.08
    éĺı
    -0.08
    Bad
    -0.08
     oppos
    -0.08
    LEAN
    -0.08
    POSITIVE LOGITS
    åħ³åĪĩ
    0.12
    æѤæŶ
    0.10
    ç¨ĭ度
    0.10
    æѤæĻĤ
    0.10
    chter
    0.09
    大å±Ģ
    0.09
    å±ĬæŶ
    0.09
    инÑĤеÑĢеÑģ
    0.09
    主ä¸ļ
    0.09
    _IA
    0.09
    Activations Density 0.044%

    No Known Activations