© 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. 54104
    Prev
    Next
    INDEX
    Explanations

    Spanish words like Juan, nación

    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
    éĴ¤
    -0.10
    驾
    -0.09
    溪
    -0.09
    anguage
    -0.09
    _generic
    -0.09
     Ñĩа
    -0.09
    æĥ³åĬŀæ³ķ
    -0.09
    elts
    -0.09
    generator
    -0.09
    è°¦
    -0.09
    POSITIVE LOGITS
    bose
    0.08
    REF
    0.08
     Kare
    0.08
    æĸ¯çī¹
    0.08
    (Level
    0.08
    åIJij社ä¼ļ
    0.08
    çī¹
    0.08
    表æĥħ
    0.08
     soc
    0.07
    edList
    0.07
    Activations Density 0.002%

    No Known Activations