© 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. 58452
    Prev
    Next
    INDEX
    Explanations

    ADA; Adele; ad_

    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
    ãģĹãģ¾ãģĦ
    -0.12
    ãģĹãģ¾ãģĨ
    -0.11
    ingly
    -0.11
    ĺ
    -0.10
    ered
    -0.10
    teen
    -0.09
    çĿij
    -0.09
    ãĥ¼ãĥī
    -0.08
    å¯Łè§ī
    -0.08
    arten
    -0.08
    POSITIVE LOGITS
    ially
    0.12
    ../
    0.12
    ends
    0.11
    vertisement
    0.11
    ively
    0.10
    VERTISEMENT
    0.10
    itional
    0.10
    oint
    0.10
    vertise
    0.10
    venture
    0.09
    Activations Density 0.132%

    No Known Activations