© 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. 30872
    Prev
    Next
    INDEX
    Explanations

    normal and expected states

    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
    ç¼Ģ
    -0.10
    åĬ¼
    -0.10
    æĢ§ä»·æ¯Ķ
    -0.10
    gles
    -0.09
    åĶ¤
    -0.09
    ç´¯
    -0.09
    åħ³åģľ
    -0.09
    кÑĢаÑģ
    -0.09
    ene
    -0.08
    çĪ¸
    -0.08
    POSITIVE LOGITS
    å¾ĪæŃ£å¸¸
    0.26
    æŃ£å¸¸çļĦ
    0.21
    æŃ£å¸¸
    0.21
     normal
    0.18
    normal
    0.16
    _normal
    0.15
     NORMAL
    0.15
    Normal
    0.14
    èĩªçĦ¶
    0.13
    NORMAL
    0.13
    Activations Density 0.255%

    No Known Activations