© 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. 31281
    Prev
    Next
    INDEX
    Explanations

    remember me

    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
    ENE
    -0.09
    åIJĦç§įåIJĦæł·
    -0.09
    _SUITE
    -0.09
    .GetInstance
    -0.09
    ä¸Ģ件äºĭæĥħ
    -0.09
    åĽ¾æłĩ
    -0.09
    çŃīåIJĦç§į
    -0.09
    mass
    -0.09
    å²±
    -0.09
    osas
    -0.09
    POSITIVE LOGITS
    åħ®
    0.08
    IOR
    0.08
    AFE
    0.08
    æī¿
    0.08
     cour
    0.08
    istung
    0.08
     forever
    0.08
    iot
    0.08
     Daly
    0.08
    ussen
    0.08
    Activations Density 0.026%

    No Known Activations