© 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. 48048
    Prev
    Next
    INDEX
    Explanations

    looking for

    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
    lez
    -0.09
    åĨ»ç»ĵ
    -0.09
     воп
    -0.08
    åijĬ
    -0.08
    oho
    -0.08
    ÙĪار
    -0.08
    rip
    -0.08
    ÑĥÑĪ
    -0.08
    AGO
    -0.08
    çŁ³æ²¹åĮĸå·¥
    -0.07
    POSITIVE LOGITS
    寻æī¾
    0.14
    寻
    0.13
     ways
    0.11
    å°ĭ
    0.11
    è§ħ
    0.11
    ways
    0.10
    寻æ±Ĥ
    0.10
    èĩĬ
    0.10
    æĸ°çļĦ
    0.10
    çŃĸ
    0.10
    Activations Density 0.146%

    No Known Activations