© 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. 54526
    Prev
    Next
    INDEX
    Explanations

    mussels and oysters

    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
    пÑĥ
    -0.11
    çĩĥ
    -0.09
    çĥŃ线
    -0.09
    eme
    -0.09
    稿
    -0.09
     puppy
    -0.08
    ighted
    -0.08
    à¹Ĥà¸ŀ
    -0.08
    ruptions
    -0.08
    ihat
    -0.08
    POSITIVE LOGITS
    çī¡
    0.13
    èĽİ
    0.11
    éŸ
    0.11
    çıįçıł
    0.10
    ysters
    0.10
    翳
    0.10
     pearls
    0.10
    港åĮº
    0.09
    é¢Ķ
    0.09
     hints
    0.09
    Activations Density 0.060%

    No Known Activations