© 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. 2315
    Prev
    Next
    INDEX
    Explanations

    synonym, synonyms, aliases

    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
    åħģ
    -0.09
    èµ°å»Ĭ
    -0.09
    ÙĨÙħ
    -0.09
    为åĩĨ
    -0.09
    íŀĪ
    -0.09
    åIJĬ
    -0.09
    -eyed
    -0.09
     nab
    -0.09
    acies
    -0.09
    isti
    -0.09
    POSITIVE LOGITS
     synonyms
    0.11
    ouro
    0.10
    åĨĹ
    0.10
    趴
    0.09
    èĩ
    0.09
     synonym
    0.09
    .dispatch
    0.09
    ship
    0.08
    ikk
    0.08
    _ld
    0.08
    Activations Density 0.038%

    No Known Activations