© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50790
    Prev
    Next
    INDEX
    Explanations

    lap words

    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
    ropy
    -0.11
    æij½
    -0.09
    ured
    -0.09
     pari
    -0.09
    iffin
    -0.08
    åıī
    -0.08
    inki
    -0.08
    uria
    -0.08
    iland
    -0.08
    iler
    -0.08
    POSITIVE LOGITS
    rum
    0.11
    rap
    0.10
    æ¤ħ
    0.10
    lace
    0.10
    ris
    0.09
    èĮ¸
    0.09
    ç½ļ
    0.09
    iente
    0.09
    illard
    0.09
    NEY
    0.09
    Activations Density 0.016%

    No Known Activations