© 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. 55577
    Prev
    Next
    INDEX
    Explanations

    Beckenheim, Beckner, Birkbeck, Seebeck

    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
    zelf
    -0.10
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.09
    lette
    -0.09
    æ°Ĺãģ«
    -0.09
    procs
    -0.09
    chandle
    -0.09
    åĮķ
    -0.08
    ìļĶ
    -0.08
    ãģıãĤĮ
    -0.08
     bạc
    -0.08
    POSITIVE LOGITS
    ingly
    0.10
    ãĤĥ
    0.09
    ãĤªãĥ³
    0.09
    она
    0.09
    -être
    0.08
    éĬ®
    0.08
    ons
    0.08
    oning
    0.08
    nesia
    0.08
    atrix
    0.08
    Activations Density 0.006%

    No Known Activations