© 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. 4287
    Prev
    Next
    INDEX
    Explanations

    situation or needs

    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
    unan
    -0.09
    åѦåĪ°
    -0.08
     Manip
    -0.08
    æıŃå¼Ģ
    -0.08
    æĸ¯
    -0.08
    interop
    -0.08
    è°ĪåĪ¤
    -0.08
    lık
    -0.08
     manipulation
    -0.08
    涵çĽĸ
    -0.08
    POSITIVE LOGITS
    æĥħåĨµ
    0.15
    æĥħåĨµè¿Ľè¡Į
    0.14
     situation
    0.13
    çĬ¶åĨµ
    0.12
    çļĦæĥħåĨµ
    0.12
    æĥħæ³ģ
    0.12
     circumstances
    0.12
    æĥħåĨµæĿ¥çľĭ
    0.11
    çī¹æ®ĬæĥħåĨµ
    0.11
    åħ·ä½ĵæĥħåĨµ
    0.10
    Activations Density 0.042%

    No Known Activations