© 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. 33297
    Prev
    Next
    INDEX
    Explanations

    government and industry entities

    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
    仲
    -0.09
    çĻ¾å¹´
    -0.09
    åħħåĪĨåıijæĮ¥
    -0.09
     rains
    -0.09
    ietf
    -0.08
     ngũ
    -0.08
    åŃĺéĩı
    -0.08
    åĽŀé¦ĸ
    -0.08
    è¿ľå¤Ħ
    -0.08
    éĺ²æ²»
    -0.08
    POSITIVE LOGITS
    产ä¸ļåŁºåľ°
    0.10
    ç¼ij
    0.09
    æĪĺçķ¥å¸ĥå±Ģ
    0.09
    åľºåIJĪ
    0.09
    æĮ¤
    0.09
    çī¹åĪ«å£°æĺİ
    0.09
    æľ¬åľŁ
    0.09
    æĽ³
    0.08
    æĭ¯æķij
    0.08
    ä¸į该
    0.08
    Activations Density 0.152%

    No Known Activations