© 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. 19306
    Prev
    Next
    INDEX
    Explanations

    attached to a

    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
    _connections
    -0.09
    ç§ĥ
    -0.09
    connection
    -0.09
    /articles
    -0.09
    mins
    -0.09
     connections
    -0.09
    éĤ¦
    -0.09
    ãĤıãģij
    -0.08
    æİī
    -0.08
    .abort
    -0.08
    POSITIVE LOGITS
     Ùħباشرة
    0.11
    æĪijä¸Ģ缴
    0.11
    ä¸įè¿ľå¤Ħ
    0.10
    èĩªèº«çļĦ
    0.10
    neath
    0.10
     táºŃn
    0.09
    åİļåİļçļĦ
    0.09
    gether
    0.09
    åĿļå®ŀçļĦ
    0.09
    çļĦåij½è¿IJ
    0.09
    Activations Density 0.128%

    No Known Activations