© 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. 31373
    Prev
    Next
    INDEX
    Explanations

    hidden, obstructed, under, behind, inside

    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
    æĭ¾
    -0.11
    åĶ¤
    -0.11
    åĶ¤éĨĴ
    -0.11
    轨
    -0.08
    达人
    -0.08
    hk
    -0.08
    ä¹IJ趣
    -0.08
    ãĤĴéĽĨ
    -0.08
    åijĬåĪ«
    -0.08
     fun
    -0.08
    POSITIVE LOGITS
    éģ®
    0.16
    æİ©çĽĸ
    0.13
    åİļåİļçļĦ
    0.13
    éļľ
    0.11
    æİ©
    0.11
    scar
    0.11
    淹没
    0.11
    è¦ĨçĽĸ
    0.10
    åİļåİļ
    0.10
    mask
    0.10
    Activations Density 0.160%

    No Known Activations