© 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. 55445
    Prev
    Next
    INDEX
    Explanations

    hope or want

    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
    飫
    -0.10
    åĩºå¤Ħ
    -0.08
    æ®Ĭ
    -0.08
    ä¸Ģå°ı
    -0.08
    éĺ²æĻĴ
    -0.08
    indsight
    -0.07
    对èĩªå·±
    -0.07
    ç²¾åĬĽ
    -0.07
    ead
    -0.07
    æĶĴ
    -0.07
    POSITIVE LOGITS
    å¸ĮæľĽéĢļè¿ĩ
    0.15
    æĹ¨åľ¨
    0.13
    å°½éĩı
    0.13
    让人们
    0.12
    åĬĽäºī
    0.12
    å¸ĮæľĽèĥ½
    0.11
    让åŃ©åŃIJ
    0.11
    让çĶ¨æĪ·
    0.11
    æŨ
    0.11
    缮çļĦåľ¨äºİ
    0.11
    Activations Density 0.072%

    No Known Activations