© 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. 35911
    Prev
    Next
    INDEX
    Explanations

    allow or provide options

    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
    PKG
    -0.10
    vie
    -0.09
    atee
    -0.09
    vil
    -0.09
    umed
    -0.09
    读æĩĤ
    -0.08
    æĪ·åı£
    -0.08
    ä¸ĢåŃĹ
    -0.08
    å¾Ń
    -0.08
     hipp
    -0.08
    POSITIVE LOGITS
    allow
    0.11
    åħģ许
    0.10
    骨头
    0.09
    Allows
    0.09
     allowing
    0.09
    让
    0.09
    Allow
    0.09
    åħģ
    0.09
    çİ»çĴĥ
    0.09
     allows
    0.09
    Activations Density 0.129%

    No Known Activations