© 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. 56431
    Prev
    Next
    INDEX
    Explanations

    HTC, Nexus, Samsung, Motorola, ZTE

    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
     fug
    -0.09
    踮
    -0.09
    è¾ħ
    -0.09
    altar
    -0.08
    ç²¾åįİ
    -0.08
    对æīĭ
    -0.08
    ãģ¨è¨Ģãģ£ãģ¦
    -0.08
    éĭª
    -0.08
    èĶļ
    -0.08
    è¿Ļ两ç§į
    -0.08
    POSITIVE LOGITS
    æij©æīĺ
    0.09
    ox
    0.08
    .android
    0.08
    па
    0.08
     Randolph
    0.08
    imuth
    0.08
    éĩĩçŁ¿çŃī
    0.08
     numeral
    0.08
    -text
    0.08
    çģ¾éļ¾
    0.08
    Activations Density 0.017%

    No Known Activations