© 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. 31714
    Prev
    Next
    INDEX
    Explanations

    copyright notice

    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
    èĩ¾
    -0.12
    slaught
    -0.10
    ãģ¤ãģĭ
    -0.09
    æĮŁ
    -0.09
    ño
    -0.09
    burn
    -0.09
    ãģĿãĤĤãģĿãĤĤ
    -0.09
    ivo
    -0.09
     Nag
    -0.09
    pret
    -0.08
    POSITIVE LOGITS
    adin
    0.09
    lek
    0.09
    éĥ¨åī¯
    0.09
    åİĨåı²æĸ°
    0.09
    lest
    0.08
    hole
    0.08
    ellers
    0.08
    éŁ³åĵį
    0.08
    ãĤĪãģĨãģª
    0.08
    indent
    0.08
    Activations Density 0.087%

    No Known Activations