© 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. 1252
    Prev
    Next
    INDEX
    Explanations

    solvent and coolant terms

    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
    OfString
    -0.09
    thes
    -0.09
     оÑĤдÑĭÑħ
    -0.09
    æ¥Ĥ
    -0.08
    wig
    -0.08
    rito
    -0.08
    athan
    -0.08
    laces
    -0.08
    大å±Ģ
    -0.08
    bers
    -0.08
    POSITIVE LOGITS
    们
    0.12
    ãģ¾ãģĹãģ¦
    0.10
    yı
    0.10
    ics
    0.10
    eln
    0.10
    们çļĦ
    0.10
    们éĥ½
    0.09
    æݧèĤ¡éĽĨåĽ¢
    0.09
    spath
    0.09
    sd
    0.09
    Activations Density 0.475%

    No Known Activations