© 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. 2337
    Prev
    Next
    INDEX
    Explanations

    box

    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
     Rogers
    -0.09
     imposs
    -0.08
    åĨ·æ¼ł
    -0.08
    ź
    -0.08
     lun
    -0.08
    ç¨Ģ
    -0.08
     Fischer
    -0.08
    è¡¡
    -0.08
    ilm
    -0.08
     balloon
    -0.08
    POSITIVE LOGITS
    	TokenName
    0.10
    mate
    0.10
    浦
    0.09
    ä»Ģä¹Īäºĭæĥħ
    0.09
    midd
    0.09
    åĮĻ
    0.09
    krit
    0.09
    楽ãģĹãģ¿
    0.09
    羨
    0.09
    иÑĢÑĥ
    0.09
    Activations Density 0.031%

    No Known Activations