© 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. 33370
    Prev
    Next
    INDEX
    Explanations

    deep sea, red hot, purple

    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
    åıijåĬ¨
    -0.10
    çĤĴä½ľ
    -0.10
    åĩºçİ°éĹ®é¢ĺ
    -0.09
    çļ¤
    -0.09
    è¶Ĭ
    -0.09
    inst
    -0.09
    åºķçĽĺ
    -0.09
    _bp
    -0.08
    ustin
    -0.08
    _PCIE
    -0.08
    POSITIVE LOGITS
    UNC
    0.09
    å¼ĢæĿ¥
    0.09
    èµ·æĿ¥
    0.09
    çĪ·
    0.08
    -off
    0.08
    çĮ©
    0.08
    alez
    0.08
    æĺİ亮
    0.08
    abras
    0.08
     bá»ģ
    0.08
    Activations Density 0.001%

    No Known Activations