© 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. 39874
    Prev
    Next
    INDEX
    Explanations

    current events and affairs

    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¸ĭä¸Ģç¯ĩ
    -0.09
     beep
    -0.09
    ob
    -0.09
    ãģ£ãģįãĤĬ
    -0.09
    ç±ģ
    -0.09
    ä¸ĭ次
    -0.08
    屦
    -0.08
    åģ¶åĥı
    -0.08
    è·¨åĽ½
    -0.08
    ç´¯äºĨ
    -0.08
    POSITIVE LOGITS
    aneous
    0.12
    izr
    0.11
    aneously
    0.10
    EMENT
    0.10
    -day
    0.10
    cy
    0.09
    ity
    0.09
    æ¯ĶåĪĨ
    0.08
    idth
    0.08
    è¾ĺ
    0.08
    Activations Density 0.190%

    No Known Activations