© 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. 27698
    Prev
    Next
    INDEX
    Explanations

    methadone

    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
    ync
    -0.09
    owers
    -0.09
    æ½
    -0.09
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.08
    elho
    -0.08
    ells
    -0.08
    per
    -0.08
    ens
    -0.08
    erv
    -0.08
    imens
    -0.08
    POSITIVE LOGITS
    åĩłæ¬¡
    0.10
    ÑİÑģÑĮ
    0.09
    æ¡´
    0.09
    TeX
    0.09
    ä»Ĺ
    0.08
    èŀ³
    0.08
    æ·Ģ
    0.08
    lage
    0.08
    ä¸Ģéĺµ
    0.08
    Ñİ
    0.08
    Activations Density 0.004%

    No Known Activations