© 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. 50631
    Prev
    Next
    INDEX
    Explanations

    presence

    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
    cy
    -0.09
    eron
    -0.09
    spath
    -0.09
    åĩĨ
    -0.08
    é¢Ĥ
    -0.08
    eva
    -0.08
    tors
    -0.08
    åĬłåħ¥äºĨ
    -0.08
    halb
    -0.08
    ilee
    -0.08
    POSITIVE LOGITS
    大åŁİå¸Ĥ
    0.10
    大å±Ģ
    0.10
    idl
    0.10
    çªł
    0.09
    OND
    0.09
    æ®Ĩ
    0.09
    iful
    0.09
    idon
    0.09
    ä¸įæħİ
    0.09
    æ®ī
    0.08
    Activations Density 0.013%

    No Known Activations