© 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. 6951
    Prev
    Next
    INDEX
    Explanations

    immune or tolerance to

    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
    fone
    -0.10
    åı£ä¸Ń
    -0.09
    æIJ¬
    -0.08
    ductive
    -0.08
    笼
    -0.08
    åIJ¬åIJ¬
    -0.08
    iler
    -0.08
    ç¿»
    -0.08
     obs
    -0.08
    æµĨ
    -0.08
    POSITIVE LOGITS
    æĬµæĬĹåĬĽ
    0.11
    身åŃIJ
    0.10
    æĬµæĬĹ
    0.10
    åѱ
    0.10
    æķıæĦŁ
    0.10
    èººåľ¨
    0.10
     potent
    0.09
    严峻
    0.09
    æ²»çĹħ
    0.09
    çĮĽçĥĪ
    0.09
    Activations Density 0.079%

    No Known Activations