© 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. 50180
    Prev
    Next
    INDEX
    Explanations

    responsible for, liable for

    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
    æĬ½
    -0.09
    åħ¬åı¸å°Ĩ
    -0.09
    缩
    -0.09
    odb
    -0.09
    .wikipedia
    -0.08
    åĥļ
    -0.08
    дол
    -0.08
    æ´ĭ
    -0.08
    éĤ£æ®µ
    -0.08
    elder
    -0.08
    POSITIVE LOGITS
    geh
    0.10
    åħ®
    0.10
    _imm
    0.10
    ä¹ĭåŁİ
    0.10
    山路
    0.09
    æĬĬè¿Ļ个
    0.09
    _RT
    0.09
    æĹłæ¯Ķ
    0.09
     neither
    0.09
    ç»ĵå®ŀ
    0.09
    Activations Density 0.039%

    No Known Activations