© 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. 48793
    Prev
    Next
    INDEX
    Explanations

    code line endings

    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
    °
    -0.10
    eel
    -0.09
    ãģĹãģ¾ãģĨ
    -0.09
    agn
    -0.09
    涤
    -0.08
    ın
    -0.08
    ador
    -0.08
    ieren
    -0.08
    asan
    -0.08
    arak
    -0.08
    POSITIVE LOGITS
    ÑģÑĤÑĮ
    0.11
    empt
    0.10
    ocities
    0.10
    Åij
    0.10
    ureka
    0.10
    zÅij
    0.10
    -scrollbar
    0.10
    çi
    0.10
    ding
    0.10
    formance
    0.10
    Activations Density 1.591%

    No Known Activations