© 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. 29812
    Prev
    Next
    INDEX
    Explanations

    HVAC repair and heating

    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
    åĩºåħ¥å¢ĥ
    -0.10
    宿
    -0.09
    ç¡Į
    -0.09
    ADM
    -0.09
    æijĶ
    -0.09
    æķ´å½¢
    -0.08
    硬åĮĸ
    -0.08
     Bust
    -0.08
    urf
    -0.08
    æ¡¢
    -0.08
    POSITIVE LOGITS
    éĩĩæļĸ
    0.15
    èĬĤèĥ½
    0.13
    å®īè£ħ
    0.13
    ä¾Ľæļĸ
    0.12
     household
    0.11
    éĶħçĤī
    0.11
    åĪ¶åĨ·
    0.11
    室å¤ĸ
    0.11
    空è°ĥ
    0.11
    家çĶ¨
    0.10
    Activations Density 0.170%

    No Known Activations