© 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. 2781
    Prev
    Next
    INDEX
    Explanations

    basis / grounds

    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
     عÙĦÙĬÙĩÙħ
    -0.10
     عÙĦÙī
    -0.10
     on
    -0.10
    OnClick
    -0.10
    OnChange
    -0.09
    è¯ī
    -0.09
    ç©´
    -0.09
     на
    -0.09
    å°ļ
    -0.09
    åľ¨è¿ĩåİ»
    -0.09
    POSITIVE LOGITS
     behalf
    0.29
     occasions
    0.17
     occasion
    0.17
    occasion
    0.15
    /off
    0.13
     basis
    0.13
     grounds
    0.12
    basis
    0.12
     ÑģайÑĤе
    0.11
     оÑģнове
    0.11
    Activations Density 0.870%

    No Known Activations