© 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. 31803
    Prev
    Next
    INDEX
    Explanations

    somehow

    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
    åĮĸè¿Ľç¨ĭ
    -0.11
    Ñıвление
    -0.09
    åı¯ä¸įæĺ¯
    -0.09
    åĬŁè¯¾
    -0.09
    ÑģÑı
    -0.08
    owed
    -0.08
    大æ¦Ĥ
    -0.08
     ìķĦë§Ī
    -0.08
    Opens
    -0.08
    ä¸Ģå®ļç¨ĭ度
    -0.08
    POSITIVE LOGITS
    èĥ¥
    0.11
    éªħ
    0.11
    éĢĬ
    0.10
     somehow
    0.10
     somew
    0.10
    å°±è¶Ĭ
    0.10
    ãĤ£
    0.10
    个å¤ļ
    0.09
    çīº
    0.09
    驺
    0.09
    Activations Density 0.009%

    No Known Activations