© 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. 38701
    Prev
    Next
    INDEX
    Explanations

    offer or invitation

    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
    éŀŃ
    -0.10
    Jud
    -0.09
    .arrow
    -0.08
    æĭīæĸ¯
    -0.08
    ortho
    -0.08
    udder
    -0.08
    Beh
    -0.08
    oku
    -0.08
    abin
    -0.08
     nhu
    -0.08
    POSITIVE LOGITS
    éĤĢ请
    0.19
    éĤĢ
    0.18
    æ©Ħæ¦Ħ
    0.15
     invitation
    0.15
    invitation
    0.14
     invitations
    0.14
     offered
    0.14
     Offer
    0.13
     Invitation
    0.13
     offer
    0.13
    Activations Density 0.081%

    No Known Activations