© 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. 35827
    Prev
    Next
    INDEX
    Explanations

    technical documentation context

    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
    .Head
    -0.09
    abic
    -0.09
    sid
    -0.09
    anonymous
    -0.09
    夯
    -0.08
    ilio
    -0.08
    ya
    -0.08
    头çĹĽ
    -0.08
     fracking
    -0.08
    peat
    -0.08
    POSITIVE LOGITS
    åĢ¼çıŃ
    0.10
    åį·
    0.10
    è°Ĺ
    0.09
    å¹²éĥ¨èģĮå·¥
    0.09
    _hdl
    0.09
    ä¸ĭä¸Ģ代
    0.09
    éŁŃ
    0.09
    æł·
    0.08
    å·
    0.08
    æľįè£ħ
    0.08
    Activations Density 0.148%

    No Known Activations