© 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. 9813
    Prev
    Next
    INDEX
    Explanations

    work in progress

    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
    ä¸Ģ审
    -0.11
    æ®Ħ
    -0.09
    åĪĨæĶ¯æľºæŀĦ
    -0.09
     изд
    -0.09
    åĬłå¿«å»ºè®¾
    -0.09
    ÑĪиб
    -0.09
    æij½
    -0.08
    orig
    -0.08
     protagon
    -0.08
    à¹ĥส
    -0.08
    POSITIVE LOGITS
    ä»įåľ¨
    0.09
    sworth
    0.09
    erset
    0.09
    _keeper
    0.09
     Lan
    0.08
    инг
    0.08
    询
    0.08
    æ¹¾
    0.08
    æĶ¾å¼ĥäºĨ
    0.08
    æł¼å°Ķ
    0.08
    Activations Density 0.011%

    No Known Activations