© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 48013
    Prev
    Next
    INDEX
    Explanations

    Jeffrey Wheeler, Lyons Capital, jpeg files

    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
    çĦ¶æĺ¯
    -0.17
    ãģĻãģ§ãģ«
    -0.10
     же
    -0.10
    Ń
    -0.10
    astic
    -0.10
    ëģĶ
    -0.10
    åŃIJéĩĮ
    -0.10
     تعاÙĦÙī
    -0.10
    ãģ¹ãģį
    -0.10
    ities
    -0.10
    POSITIVE LOGITS
    å©¿
    0.12
    说æĺ¯
    0.11
    ingly
    0.11
    ally
    0.10
    matic
    0.10
    ãģĹãģ¾ãģĨ
    0.10
    ODY
    0.09
    Carthy
    0.09
    侧ç»ĵæŀĦæĢ§
    0.09
    лег
    0.09
    Activations Density 0.161%

    No Known Activations