© 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. 6788
    Prev
    Next
    INDEX
    Explanations

    airport, rights, authority, stadium, Jersey

    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
    igner
    -0.10
    è¾¹éĻħ
    -0.10
    çİ°åľº
    -0.09
    æĺ¯éĿŀ
    -0.09
    å¼Ĭ
    -0.09
    uard
    -0.09
    çı¾åł´
    -0.09
    欤
    -0.09
    çī§
    -0.09
    çİĩè¾¾åĪ°
    -0.09
    POSITIVE LOGITS
    ä¹IJåĽŃ
    0.08
     Belly
    0.08
     hardest
    0.08
    èĽ¤
    0.08
    æĸ°æł¼å±Ģ
    0.08
    åķĦ
    0.08
    åĬ³
    0.08
    å¢ŀéķ¿
    0.08
    æķ·
    0.08
     rak
    0.08
    Activations Density 0.117%

    No Known Activations