© 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. 27392
    Prev
    Next
    INDEX
    Explanations

    isolate, quarantine, immobilize, neutralize, containment

    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
    IMS
    -0.10
    éĥijéĩį
    -0.09
    .ci
    -0.09
    èĵIJ
    -0.09
     Dys
    -0.09
    noop
    -0.09
    竣工
    -0.09
    _ten
    -0.09
    ׼×Ļ
    -0.09
    premium
    -0.08
    POSITIVE LOGITS
    éļĶ离
    0.12
    ä½ıäºĨ
    0.12
     isol
    0.11
    åѤç«ĭ
    0.10
    翦
    0.10
    ä½ı
    0.10
    éĺ»
    0.10
    5
    0.10
    éĶģå®ļ
    0.10
    çݺ
    0.10
    Activations Density 0.085%

    No Known Activations