© 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. 58243
    Prev
    Next
    INDEX
    Explanations

    compost production

    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
    hart
    -0.10
    outs
    -0.10
    лив
    -0.09
    å¹ķ
    -0.09
     Lesser
    -0.09
    ufs
    -0.09
    ances
    -0.09
    بÙĪ
    -0.09
     scout
    -0.08
    å¹´æľ«
    -0.08
    POSITIVE LOGITS
    ä»ħä¾Ľ
    0.09
    åĩºå±Ģ
    0.09
    第ä¸Ģ书记
    0.09
    ä»»æķĻ
    0.09
    aris
    0.09
    åĹ
    0.09
    家åºŃ
    0.08
    èĮ¶åĽŃ
    0.08
    mates
    0.08
    éĴ¢ç»ĵæŀĦ
    0.08
    Activations Density 0.003%

    No Known Activations