© 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. 10490
    Prev
    Next
    INDEX
    Explanations

    needs analysis and specification

    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¸įåIJ«
    -0.09
    StringValue
    -0.08
    ож
    -0.08
    ä¸ŃåĽ½çī¹èī²
    -0.08
    à¸ŀล
    -0.08
    ä»ħä¾Ľ
    -0.07
    ibe
    -0.07
    æĮº
    -0.07
     Lair
    -0.07
    erver
    -0.07
    POSITIVE LOGITS
    客æĪ·éľĢæ±Ĥ
    0.22
    éľĢæ±Ĥ
    0.19
    çļĦéľĢæ±Ĥ
    0.16
    å¸ĤåľºéľĢæ±Ĥ
    0.16
    æij¸
    0.13
    è°ĥçłĶ
    0.13
     Needs
    0.12
     needs
    0.12
     demand
    0.12
    Needs
    0.11
    Activations Density 0.100%

    No Known Activations