© 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. 5142
    Prev
    Next
    INDEX
    Explanations

    NVIDIA company and products

    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
    è£ģ
    -0.11
    æħĪ
    -0.10
    åĽ½åľŁèµĦæºIJ
    -0.10
    è´¤
    -0.10
    èĪ¶
    -0.10
    åıĪèĥ½
    -0.09
    /books
    -0.09
    antas
    -0.09
    lein
    -0.09
    wipe
    -0.09
    POSITIVE LOGITS
    ibus
    0.09
     Aleppo
    0.09
    iously
    0.08
    身æĹģ
    0.08
    èĬĿ麻
    0.08
    parator
    0.08
    åĺīåħ´
    0.07
    Untitled
    0.07
    Ñģлед
    0.07
    èĿł
    0.07
    Activations Density 0.003%

    No Known Activations