© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52431
    Prev
    Next
    INDEX
    Explanations

    personal computers and laptops

    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
    arent
    -0.09
    èĬĴ
    -0.09
    çīĮ
    -0.09
    çĽ¸å£°
    -0.09
    缬
    -0.08
    çļ±çº¹
    -0.08
    貫
    -0.08
    /rfc
    -0.08
    æĺĵ
    -0.08
    ynet
    -0.08
    POSITIVE LOGITS
    çĶµèĦij
    0.20
    鼻èħ¦
    0.15
    计ç®Ĺæľº
    0.14
     ì»´íĵ¨íĦ°
    0.14
    ç¬Ķè®°æľ¬
    0.14
     laptop
    0.14
     computer
    0.14
     computers
    0.13
    æ¡ĮéĿ¢
    0.13
    ãĥijãĤ½ãĤ³ãĥ³
    0.13
    Activations Density 0.220%

    No Known Activations