© 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. 33223
    Prev
    Next
    INDEX
    Explanations

    meteorites, meteorology, meteorologist, meteor app

    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
    èľ©
    -0.09
    å¹ħ
    -0.09
    ses
    -0.09
    æŁıæŀĹ
    -0.08
    âľħ
    -0.08
    ä¿©
    -0.08
    utra
    -0.08
    档次
    -0.08
    _PCM
    -0.08
    å±ĢéĿ¢
    -0.08
    POSITIVE LOGITS
    chalk
    0.10
    ological
    0.10
     благод
    0.09
    plet
    0.09
    BOARD
    0.09
    ically
    0.09
    boarding
    0.09
    èIJ½åľ¨
    0.09
    izr
    0.09
    ä¸ĩåĪĨ
    0.09
    Activations Density 0.009%

    No Known Activations