© 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. 32490
    Prev
    Next
    INDEX
    Explanations

    nail polish, nails, fungi, light emitting

    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
     вн
    -0.10
    éĢĶå¾Ħ
    -0.09
    éĻį
    -0.09
    /mit
    -0.09
    HN
    -0.08
    顶
    -0.08
    ä¸į失
    -0.08
    æIJ¬åĪ°
    -0.08
    çĤĬ
    -0.08
    çŁ¿æ³īæ°´
    -0.08
    POSITIVE LOGITS
    æĭĩ
    0.10
    icorn
    0.10
    æĮĩçĶ²
    0.09
    éºĿ
    0.09
     Herc
    0.09
    çļĦçłĶåıij
    0.09
    glass
    0.08
    å®īå®ģ
    0.08
    趾
    0.08
    ìĭľ
    0.08
    Activations Density 0.050%

    No Known Activations