© 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. 48648
    Prev
    Next
    INDEX
    Explanations

    abandonment and related 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
    ä¸įåĩºæĿ¥
    -0.09
    妥åĸĦ
    -0.09
    .Scale
    -0.08
    _marshall
    -0.08
    ä¹ł
    -0.08
    argas
    -0.08
    çĿ¦
    -0.08
    ucci
    -0.08
    mpp
    -0.08
    /play
    -0.08
    POSITIVE LOGITS
    æĬĽå¼ĥ
    0.11
    å¼ĥ
    0.10
     abandon
    0.10
    æ£Ħ
    0.10
    éģĹ
    0.10
    åĢ¼å®Ī
    0.09
     abandonment
    0.09
    åİŁåĪĻ
    0.09
     abandoned
    0.09
    oval
    0.09
    Activations Density 0.023%

    No Known Activations