© 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. 7549
    Prev
    Next
    INDEX
    Explanations

    nation has or of

    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
    åľ°å¸¦
    -0.10
    æľŁåĨħ
    -0.10
    èĢģ人家
    -0.09
    çıŃåŃIJ
    -0.09
    念头
    -0.08
    ond
    -0.08
    оп
    -0.08
    ç¿ħ
    -0.08
     cog
    -0.08
    å°¼äºļ
    -0.08
    POSITIVE LOGITS
    wide
    0.16
    naire
    0.15
    -wide
    0.14
    nement
    0.14
    hood
    0.14
    istic
    0.13
    çĦ¶æĺ¯
    0.12
    ellt
    0.11
    naires
    0.11
    ally
    0.10
    Activations Density 0.015%

    No Known Activations