© 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. 57098
    Prev
    Next
    INDEX
    Explanations

    m followed by a number

    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
     congress
    -0.09
    ä¸Ģå¤ľ
    -0.09
    ÙĨÙĬ
    -0.09
     borderTop
    -0.09
    éĺĹ
    -0.09
    зав
    -0.09
     Alberto
    -0.09
    åķĨåºĹ
    -0.08
    æķijæĬ¤
    -0.08
    客æ°Ķ
    -0.08
    POSITIVE LOGITS
    obile
    0.10
    rf
    0.09
    vell
    0.09
    趸
    0.09
    rv
    0.08
     OBJ
    0.08
    åĽ´
    0.08
    æľĪä¸Ń
    0.08
    .nih
    0.08
    åĦĺ
    0.08
    Activations Density 0.130%

    No Known Activations