© 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. 18849
    Prev
    Next
    INDEX
    Explanations

    drop in value or quantity

    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
    è¨Ĺ
    -0.09
    åĮĸè¿Ľç¨ĭ
    -0.09
    ONSE
    -0.09
    å¯Ħæīĺ
    -0.09
    apos
    -0.09
    ither
    -0.09
    为æŃ¢
    -0.08
    jur
    -0.08
     Grü
    -0.08
     ëĵ¤
    -0.08
    POSITIVE LOGITS
    åĴĮå®ĮåĸĦ
    0.11
    nell
    0.10
    aru
    0.10
    ierre
    0.10
    lish
    0.10
    jaw
    0.09
    æŁ¥çľĭæĽ´å¤ļ
    0.09
    lights
    0.09
    -offs
    0.08
    backs
    0.08
    Activations Density 0.022%

    No Known Activations