© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51273
    Prev
    Next
    INDEX
    Explanations

    biblical book names

    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
    å©Ĩ
    -0.09
    ç»´
    -0.08
    ilded
    -0.08
    åİŁåĪĽ
    -0.08
    çĶ°
    -0.08
    ä¾ł
    -0.08
    çķĻ
    -0.08
     thừa
    -0.08
    ora
    -0.08
     Fre
    -0.08
    POSITIVE LOGITS
    ä¸Ńæĸ°
    0.09
    æ¦ľ
    0.09
     Territories
    0.09
    ippi
    0.09
    çĴľ
    0.09
    ä¸Ńéĵģ
    0.08
    大家ä¸Ģèµ·
    0.08
     Haut
    0.08
    éĤ£æ®µ
    0.08
    Brightness
    0.08
    Activations Density 0.023%

    No Known Activations