© 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. 58036
    Prev
    Next
    INDEX
    Explanations

    start with

    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
    éļıå¤Ħ
    -0.11
    éļıæŶéļı
    -0.11
    éļıæŶéļıåľ°
    -0.10
    çľĭçĤ¹
    -0.09
    ÑģÑĤвеннÑĭй
    -0.09
    éĢ¡
    -0.09
    å¤ļå±Ĥ次
    -0.09
    /mp
    -0.09
     Bare
    -0.09
    æıIJåīį
    -0.09
    POSITIVE LOGITS
    .checkNotNull
    0.10
     basics
    0.10
    å¥
    0.10
    èĨĪ
    0.09
    åŁºæľ¬åİŁåĪĻ
    0.09
    éĽĦ
    0.08
    éķ¿å®ī
    0.08
    _LAT
    0.08
    endo
    0.08
     Gir
    0.08
    Activations Density 0.042%

    No Known Activations