© 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. 58218
    Prev
    Next
    INDEX
    Explanations

    patent citation B2

    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
    æ¶Įçİ°
    -0.08
    迳
    -0.08
    daq
    -0.07
     trickle
    -0.07
    æ±°
    -0.07
    æ¼Ĩ
    -0.07
    åĮĸè¿Ľç¨ĭ
    -0.07
    tees
    -0.07
    edian
    -0.07
    osity
    -0.07
    POSITIVE LOGITS
    tips
    0.10
     Cristiano
    0.10
    åĴĮ个人
    0.09
    è·Ľ
    0.09
    orda
    0.09
    esium
    0.09
    uin
    0.09
    æĺİæ¸ħ
    0.09
    è¶Ķ
    0.09
    ç»ĪçĶŁ
    0.09
    Activations Density 0.189%

    No Known Activations