© 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. 23560
    Prev
    Next
    INDEX
    Explanations

    or later

    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
    缺åı£
    -0.09
    aged
    -0.09
    çıįæĥľ
    -0.09
    çĥ¦
    -0.08
    avig
    -0.08
    åı¯ä¾Ľ
    -0.08
    reno
    -0.08
    اÙĦÙģ
    -0.08
    åij¨
    -0.08
    _tabs
    -0.08
    POSITIVE LOGITS
    说äºĨ
    0.10
    ä¸ĢèĦļ
    0.10
    çļĦæĥ³æ³ķ
    0.09
    æ®ĩ
    0.09
    åĥŃ
    0.09
    å¿ł
    0.08
    çļĦåį°è±¡
    0.08
    isd
    0.08
     depending
    0.08
    uelle
    0.08
    Activations Density 0.013%

    No Known Activations