© 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. 38361
    Prev
    Next
    INDEX
    Explanations

    encapsulated, enclosing, encrusted

    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
    ãģĹãģ¾ãģĨ
    -0.11
    fully
    -0.11
    æĢģ
    -0.10
    -0.10
    çŀ©çĽ®
    -0.09
    olic
    -0.08
     ComVisible
    -0.08
    ing
    -0.08
    ãģĦãģı
    -0.08
    çľģéĴ±
    -0.08
    POSITIVE LOGITS
    ounters
    0.13
    odings
    0.11
    rypted
    0.11
    (enc
    0.10
    ourage
    0.10
    PRI
    0.10
    oders
    0.10
    绶
    0.10
    ounter
    0.10
    prises
    0.10
    Activations Density 0.052%

    No Known Activations