© 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. 62510
    Prev
    Next
    INDEX
    Explanations

    . // comments

    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
    å±İ
    -0.09
    doch
    -0.09
    reta
    -0.09
    ahoo
    -0.09
    hey
    -0.08
    ëĦ·
    -0.08
    åĢĻ
    -0.08
    .multiply
    -0.08
    (PR
    -0.08
    åħ¨åľº
    -0.08
    POSITIVE LOGITS
    round
    0.09
     Round
    0.09
    伸åĩº
    0.09
    è¯Ħè®®
    0.09
    害
    0.08
     round
    0.08
    篷
    0.08
    AIM
    0.08
    _ROUND
    0.08
    åħ³èĬĤ
    0.08
    Activations Density 0.090%

    No Known Activations