© 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. 31437
    Prev
    Next
    INDEX
    Explanations

    names ending in s

    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
    åĪĨåĪ«æĺ¯
    -0.10
    æĺıè¿·
    -0.10
    侵害
    -0.09
    .resp
    -0.09
    VERSE
    -0.09
    _INFORMATION
    -0.09
    ä¸įæŃ»
    -0.09
    åĪ¤æĸŃ
    -0.09
    ivol
    -0.09
    èĭ¦æģ¼
    -0.09
    POSITIVE LOGITS
    able
    0.09
    ple
    0.09
    าà¸ģ
    0.08
    ity
    0.08
    cape
    0.08
    à¹Į
    0.08
    ponsored
    0.08
    æİı
    0.08
    äºĨä¸Ģ份
    0.08
    踮
    0.07
    Activations Density 0.122%

    No Known Activations