© 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. 1631
    Prev
    Next
    INDEX
    Explanations

    subtle / discrete / overt

    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
    alon
    -0.10
    ãng
    -0.09
    è·¨
    -0.09
    æİĪäºĪ
    -0.09
    ableObject
    -0.09
    лев
    -0.09
    олоÑģ
    -0.08
    ä¸Ģ段
    -0.08
    Ñģол
    -0.08
    以人为
    -0.08
    POSITIVE LOGITS
    å¼łæī¬
    0.13
    å¤¸å¼ł
    0.12
    éĻIJ度
    0.10
    èĢģ人家
    0.10
    åIJİèĢħ
    0.10
    åĸĩåıŃ
    0.10
    è¿ĩåĪĨ
    0.10
    åĸ§
    0.10
    硬件
    0.09
    çĶŁæĢķ
    0.09
    Activations Density 0.039%

    No Known Activations