© 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. 11602
    Prev
    Next
    INDEX
    Explanations

    allow or let

    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
    lick
    -0.08
    æ½ľ
    -0.08
     tess
    -0.07
    åĬłæ²¹
    -0.07
    .coeff
    -0.07
    é£Ĵ
    -0.07
    æİ¥å¾ħ
    -0.07
    迪æĭľ
    -0.07
     Courier
    -0.07
    mal
    -0.07
    POSITIVE LOGITS
    å±ĬæŶ
    0.13
    åħį
    0.11
    åħ¶å®ĥéĹ®é¢ĺ
    0.11
    å«Ĥ
    0.11
    åŀĤ
    0.10
    æ¥ļ
    0.10
    åĪ°æŶåĢĻ
    0.10
    æī¿è®¤
    0.10
    æ¡Ĩæŀ¶åįıè®®
    0.10
    派驻
    0.09
    Activations Density 0.082%

    No Known Activations