© 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. 2321
    Prev
    Next
    INDEX
    Explanations

    heating and cooling systems

    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
    缨
    -0.11
    ÅĪ
    -0.10
    è§Ħ模æľĢ大
    -0.10
    åŀĥåľ¾æ¡¶
    -0.09
    å¿Ļ
    -0.09
    /lic
    -0.09
    è§ĩ
    -0.09
    æģķ
    -0.09
    noon
    -0.09
    æįIJ
    -0.09
    POSITIVE LOGITS
    ä¾Ľæļĸ
    0.13
    æļĸæ°Ķ
    0.12
    æļĸ
    0.12
    åıĸæļĸ
    0.12
    温æļĸ
    0.11
    åĨ¬å¤©
    0.11
    åĨ¬åŃ£
    0.11
    æļĸå¿ĥ
    0.11
     heating
    0.11
     Heating
    0.10
    Activations Density 0.041%

    No Known Activations