© 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. 39064
    Prev
    Next
    INDEX
    Explanations

    biblatex references

    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
    ingly
    -0.11
    åĽłä¸ºå¥¹
    -0.10
     mẽ
    -0.10
    ules
    -0.09
    igers
    -0.09
    çļ¿
    -0.09
    ably
    -0.09
    baugh
    -0.09
    uff
    -0.08
    ä¸Ģæł¹
    -0.08
    POSITIVE LOGITS
    ÂŃi
    0.10
    çĬĬ
    0.10
    å¹Į
    0.09
    lio
    0.09
    itat
    0.09
    èĩªæ²»åĮº
    0.09
    matic
    0.09
    è¹²
    0.09
    aries
    0.09
    ãģĹãģ¾ãģĨ
    0.09
    Activations Density 0.018%

    No Known Activations