© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8981
    Prev
    Next
    INDEX
    Explanations

    north 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
    æ®Ħ
    -0.10
    éģĽ
    -0.09
    åį´åıijçİ°
    -0.09
    Gateway
    -0.09
    è·ĥ
    -0.08
     van
    -0.08
    éĢīè´Ń
    -0.08
    å¼Ģçİ©ç¬ij
    -0.08
    éģģ
    -0.08
    æģ£
    -0.08
    POSITIVE LOGITS
    رش
    0.10
    éĥĹ
    0.09
    çĭ¬å®¶
    0.08
    _dyn
    0.08
    ç«Ļéķ¿
    0.08
    æĶ¶åĽŀ
    0.08
    /mat
    0.08
    .tk
    0.08
    æĪĸå¤ļ
    0.08
    utas
    0.08
    Activations Density 0.042%

    No Known Activations