© 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. 1419
    Prev
    Next
    INDEX
    Explanations

    avoiding things

    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
    æŀ·
    -0.10
     веÑĩ
    -0.10
     Fetish
    -0.10
    åŁ¹
    -0.10
     Fet
    -0.09
    æķĻè®Ń
    -0.09
    è§ģè¯Ĩ
    -0.09
    éĽĨè£ħ
    -0.09
    æĦıæĥ³ä¸įåĪ°
    -0.09
    éľĢæ±Ĥ
    -0.08
    POSITIVE LOGITS
    éĢĥéģ¿
    0.20
    躲éģ¿
    0.18
    éģ¿
    0.17
    åĽŀéģ¿
    0.16
     avoidance
    0.16
    æĭĸ延
    0.14
    è§Ħéģ¿
    0.14
    éģ¿å¼Ģ
    0.13
    躲
    0.13
    å»¶è¿Ł
    0.13
    Activations Density 0.099%

    No Known Activations