© 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. 56757
    Prev
    Next
    INDEX
    Explanations

    Plat and platt words

    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
    aled
    -0.09
    渣
    -0.08
    .cloudflare
    -0.08
    oleon
    -0.08
    寻常
    -0.08
    алÑĮ
    -0.08
    ousel
    -0.08
    åħ¶æ¬¡æĺ¯
    -0.08
    åīįåĪĹ
    -0.08
    æ®ĸ
    -0.08
    POSITIVE LOGITS
    smouth
    0.10
    amp
    0.09
    踵
    0.09
    º
    0.09
    еж
    0.09
    çĶµè§Ĩæľº
    0.08
    ãĥĭãĥ³ãĤ°
    0.08
    thumbs
    0.08
    oney
    0.08
    enge
    0.08
    Activations Density 0.008%

    No Known Activations