© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38217
    Prev
    Next
    INDEX
    Explanations

    appropriate, effective, desired, safe

    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
    ä¸įåħ·å¤ĩ
    -0.09
    çĻ½éĽª
    -0.09
    .BorderColor
    -0.09
    tat
    -0.09
    è¦ģä¹Ī
    -0.08
    å·²ç»ıè¾¾åĪ°
    -0.08
    æ½ľèĥ½
    -0.08
    ä¹Łåıªæĺ¯
    -0.08
    京åŁİ
    -0.08
    ç«ĭ足
    -0.08
    POSITIVE LOGITS
    åĪĴç®Ĺ
    0.11
    好äºĭ
    0.10
    å¿ħè¦ģ
    0.10
     necessary
    0.10
    çī¹æĸ¯
    0.10
    ÙĬÙĪ
    0.09
    è¾ĥ好
    0.09
    æľīå¿ħè¦ģ
    0.09
     better
    0.09
    çĪ±ç¾İ
    0.09
    Activations Density 0.204%

    No Known Activations