© 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. 11210
    Prev
    Next
    INDEX
    Explanations

    lead or advantage

    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
    oks
    -0.11
     Kendrick
    -0.09
    elin
    -0.09
    ELS
    -0.09
    äºĭåħĪ
    -0.09
     пÑĢиÑĩ
    -0.09
    è°¦
    -0.09
    /cl
    -0.09
     HttpRequest
    -0.09
    els
    -0.09
    POSITIVE LOGITS
    èħĬ
    0.09
    gement
    0.08
     Bers
    0.08
    é»Ħæĺı
    0.08
    .dy
    0.08
    åī§
    0.08
    饺
    0.08
    伶
    0.07
    屯
    0.07
    Bes
    0.07
    Activations Density 0.003%

    No Known Activations