© 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. 32775
    Prev
    Next
    INDEX
    Explanations

    heating water and apparatus

    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
    illis
    -0.11
     Ñģил
    -0.10
    -minded
    -0.10
    wers
    -0.08
    ibil
    -0.08
    èĿĩ
    -0.08
    usk
    -0.08
    orna
    -0.08
    ä¸İæŶ
    -0.08
    ading
    -0.08
    POSITIVE LOGITS
    çĶŁæ´»åľ¨
    0.11
    çħ§äº®
    0.09
    æĸ¯é¡¿
    0.09
    /de
    0.09
    LINK
    0.08
    åĻ¨
    0.08
    oth
    0.08
    å·§
    0.08
    çłŃ
    0.08
    contr
    0.08
    Activations Density 0.040%

    No Known Activations