© 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. 4442
    Prev
    Next
    INDEX
    Explanations

    currently active or ongoing

    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
    åħ½
    -0.09
    æĸ¯åŁº
    -0.09
    è¡£
    -0.09
    posal
    -0.09
    elman
    -0.09
    éĹªåħī
    -0.08
    BEST
    -0.08
     Hammond
    -0.08
     RIGHTS
    -0.08
    å¿Ĺ强
    -0.08
    POSITIVE LOGITS
    æŃ£åľ¨è¿Ľè¡Į
    0.21
    æŃ£åľ¨
    0.18
     active
    0.15
     ongoing
    0.15
     underway
    0.14
    InProgress
    0.13
     Äijang
    0.13
     outstanding
    0.13
    active
    0.12
    _active
    0.12
    Activations Density 0.152%

    No Known Activations