© 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. 3720
    Prev
    Next
    INDEX
    Explanations

    material things, progress, support, properties

    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
    èĦļä¸ĭ
    -0.10
    离
    -0.10
    çł
    -0.08
    ounc
    -0.08
    åĵĪä½Ľ
    -0.08
    patrick
    -0.08
    æĸĮ
    -0.08
    è§ĨåIJ¬
    -0.08
     unlock
    -0.07
    acad
    -0.07
    POSITIVE LOGITS
    ity
    0.10
    .fhir
    0.10
    iens
    0.09
    ä¾£
    0.09
    æ·Į
    0.09
    å¦ĥ
    0.09
    ResourceId
    0.09
     Lau
    0.09
    ãģij
    0.09
    åĴª
    0.09
    Activations Density 0.016%

    No Known Activations