© 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. 33719
    Prev
    Next
    INDEX
    Explanations

    concentration-dependent patient-driven

    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
     outright
    -0.09
    IPA
    -0.09
    osti
    -0.09
    -nil
    -0.09
    éĺij
    -0.09
    ents
    -0.09
     اÙĦطبÙĬعÙĬ
    -0.08
    çļĦåı¯èĥ½æĢ§
    -0.08
    Nil
    -0.08
    PrototypeOf
    -0.08
    POSITIVE LOGITS
     friendly
    0.11
     Friendly
    0.10
    åıĭ好
    0.10
    é¢ĨåħĪçļĦ
    0.09
    缸åħ³çļĦ
    0.09
    缸å½ĵ
    0.09
    friendly
    0.09
    _FRIEND
    0.09
     driven
    0.09
    Friendly
    0.09
    Activations Density 0.441%

    No Known Activations