© 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. 32316
    Prev
    Next
    INDEX
    Explanations

    finding

    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
    acin
    -0.10
    busy
    -0.10
    稷
    -0.09
     Pra
    -0.09
    arin
    -0.09
    enia
    -0.09
     Dame
    -0.08
     воÑĤ
    -0.08
     Moor
    -0.08
    .Handled
    -0.08
    POSITIVE LOGITS
    éĢĤåIJĪèĩªå·±
    0.11
    åIJĪéĢĤçļĦ
    0.10
    å¤ļäºĨ
    0.10
    åIJĪéĢĤ
    0.09
    åĴ½
    0.09
    æ°¸ä¹ħ
    0.09
     Holiday
    0.09
    åĹ£
    0.08
    è¦ģåģļåĪ°
    0.08
    éĻĽ
    0.08
    Activations Density 0.035%

    No Known Activations