© 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. 51336
    Prev
    Next
    INDEX
    Explanations

    Persian سÙĩج

    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
    toc
    -0.09
    åĵªæĢķæĺ¯
    -0.09
    ä¹ĥèĩ³
    -0.08
    .tracks
    -0.08
    åĽłåľ°
    -0.08
    å½¢åĬ¿
    -0.08
    åĵªæĢķ
    -0.08
    éģĹçķĻ
    -0.08
    ä¸įä¹ħ
    -0.08
    æĻ¯å¾·éķĩ
    -0.08
    POSITIVE LOGITS
     glor
    0.09
     kad
    0.08
    èĹ©
    0.08
    resar
    0.08
    سÙĦاÙħ
    0.08
    ãģ£ãģ¡
    0.08
    ä»»æĢ§
    0.07
     Voor
    0.07
    astic
    0.07
    çijĻ
    0.07
    Activations Density 0.128%

    No Known Activations