© 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. 17691
    Prev
    Next
    INDEX
    Explanations

    don't care or who cares

    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
    ivr
    -0.10
    ëľ»
    -0.09
    åķĨä¼ļ
    -0.09
    apel
    -0.09
    ssel
    -0.09
    _SD
    -0.08
    为äºĨæĽ´å¥½
    -0.08
    ernity
    -0.08
    rees
    -0.08
    awi
    -0.08
    POSITIVE LOGITS
    lessly
    0.13
    fully
    0.12
     whether
    0.10
    äºĽä»Ģä¹Ī
    0.10
    wash
    0.09
    ingly
    0.09
     about
    0.09
    å¾Ĺèµ·
    0.09
    ably
    0.09
    eka
    0.09
    Activations Density 0.007%

    No Known Activations