© 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. 48656
    Prev
    Next
    INDEX
    Explanations

    Bologna city names

    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
    颢
    -0.09
    /sw
    -0.09
    eil
    -0.09
    åĨ·èĹı
    -0.09
    éķĩæĶ¿åºľ
    -0.08
    mdl
    -0.08
    Fil
    -0.08
    otta
    -0.08
    ler
    -0.08
    èī¯å¿ĥ
    -0.08
    POSITIVE LOGITS
    pher
    0.10
    èĥª
    0.09
    åıł
    0.09
    pheric
    0.08
    _serialize
    0.08
    CAM
    0.08
    isión
    0.08
    èĵ¬åĭĥ
    0.08
    åı¯æĢľ
    0.08
     Bright
    0.08
    Activations Density 0.005%

    No Known Activations