© 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. 18998
    Prev
    Next
    INDEX
    Explanations

    play

    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
    fte
    -0.09
    æķĻè®Ń
    -0.09
     eBooks
    -0.09
    isations
    -0.09
    è½°
    -0.09
    éĺħè§Ī
    -0.09
    енн
    -0.09
    åij±
    -0.09
    Ñģен
    -0.08
    aker
    -0.08
    POSITIVE LOGITS
    alue
    0.09
    èµī
    0.09
    èĢ½
    0.09
    åłij
    0.09
    æĸ¹éĴĪ
    0.08
    ally
    0.08
     Massive
    0.08
    é¥Ń
    0.08
    ler
    0.08
    ern
    0.08
    Activations Density 0.046%

    No Known Activations