© 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. 50161
    Prev
    Next
    INDEX
    Explanations

    rotate or rotation

    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
    utom
    -0.09
    çŁŃæŶéĹ´åĨħ
    -0.09
    hots
    -0.09
    èģĮä¸ļéģĵå¾·
    -0.09
    rips
    -0.09
    halt
    -0.09
    born
    -0.08
    åİŁæĿ¥æĺ¯
    -0.08
    poon
    -0.08
    ennon
    -0.08
    POSITIVE LOGITS
    ting
    0.11
    ìľ¨
    0.11
    yna
    0.10
    terdam
    0.10
    ï¸ı
    0.10
    æŁ½
    0.10
    鬣
    0.09
    ally
    0.09
    ãĥ¼ãĤ·ãĥ§ãĥ³
    0.09
     Dix
    0.09
    Activations Density 0.053%

    No Known Activations