© 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. 54626
    Prev
    Next
    INDEX
    Explanations

    names ending in -ton or -arton

    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
    istan
    -0.08
    ners
    -0.08
    .ev
    -0.08
    çĨ¬
    -0.08
    IDER
    -0.08
    çŀ¥
    -0.08
    æĸ¯çī¹
    -0.08
    hör
    -0.08
    çĻ¾å¹´
    -0.08
    Axis
    -0.08
    POSITIVE LOGITS
    -
    0.16
    âĢIJ
    0.14
    Ö¾
    0.11
    âĤĭ
    0.11
    -x
    0.10
    âĢij
    0.09
    éĦĦ
    0.08
    –
    0.08
    -night
    0.08
    {-
    0.08
    Activations Density 0.426%

    No Known Activations