© 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. 3911
    Prev
    Next
    INDEX
    Explanations

    economic and development organizations

    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
    é¡·
    -0.09
    .elements
    -0.08
    åı·åı¬
    -0.08
    èı½
    -0.08
    establish
    -0.08
    ('=
    -0.08
    åħĥç´ł
    -0.07
     eternity
    -0.07
     establishing
    -0.07
    itel
    -0.07
    POSITIVE LOGITS
    è¡Įéķ¿
    0.10
    åĨ¶
    0.10
    ä¿¡è´·
    0.10
    贷款
    0.10
    dlg
    0.09
    è¡¢
    0.09
     DIAG
    0.09
    æĬķè¡Į
    0.09
    è´·
    0.09
    æĻºåĬĽ
    0.09
    Activations Density 0.040%

    No Known Activations