© 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. 27851
    Prev
    Next
    INDEX
    Explanations

    your team, patients, members

    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
    éģĹ产
    -0.08
    tru
    -0.08
    squeeze
    -0.08
    äºĨä»ĸçļĦ
    -0.08
     storyboard
    -0.08
    exe
    -0.08
    Cum
    -0.08
     Cure
    -0.08
    (QObject
    -0.08
    _sparse
    -0.08
    POSITIVE LOGITS
    åĬ¨åijĺ
    0.11
    è¾ĸåĮº
    0.10
    æ°ijæĶ¿
    0.10
     Flesh
    0.09
    æľ¬åľ°
    0.09
    éĤĢ
    0.09
     Mim
    0.09
    è¾ĸåĮºåĨħ
    0.09
    atab
    0.09
    èĶij
    0.09
    Activations Density 0.101%

    No Known Activations