© 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. 48676
    Prev
    Next
    INDEX
    Explanations

    Crown titles and associated terms

    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
    ges
    -0.10
    ãģĦãģĨ
    -0.10
    ision
    -0.09
    à¹Ħà¸Ĺย
    -0.09
    ronic
    -0.09
    zem
    -0.09
    continued
    -0.08
    çĶ¨æ°´
    -0.08
     вÑģ
    -0.08
    gest
    -0.08
    POSITIVE LOGITS
    ings
    0.14
    umer
    0.11
    /or
    0.10
    幡
    0.10
    INGS
    0.10
    less
    0.10
    LESS
    0.10
    arl
    0.09
    åĨķ
    0.09
    éĻĽä¸ĭ
    0.09
    Activations Density 0.012%

    No Known Activations