© 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. 50440
    Prev
    Next
    INDEX
    Explanations

    is a/an/the

    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
    ä»İä¸Ń
    -0.10
    upid
    -0.09
    ä½£
    -0.09
    berger
    -0.08
    aper
    -0.08
    ä½łçľĭ
    -0.08
    å¦Ĥæŀľä½ł
    -0.08
    aris
    -0.08
    è¦ģä¹Ī
    -0.08
    rible
    -0.08
    POSITIVE LOGITS
    èĵ¦
    0.10
    è·ĥ
    0.10
    第ä¸ĢæĿ¡
    0.09
    çįł
    0.09
    æĪijåıĪ
    0.09
    èĭ±æīį
    0.08
    æ¶ī
    0.08
    اØŃت
    0.08
    ä¿Ĺ
    0.08
    è¿Ļæĺ¯æĪij
    0.08
    Activations Density 0.661%

    No Known Activations