© 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. 2330
    Prev
    Next
    INDEX
    Explanations

    stack and stack frames

    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
    çĸı
    -0.11
    æ»ŀåIJİ
    -0.09
    èĤ¢
    -0.09
    ç©°
    -0.08
    medi
    -0.08
    éĻĮ
    -0.08
    gua
    -0.08
    pread
    -0.08
    åŃ¦ä¹łæĪIJ绩
    -0.08
    utorial
    -0.08
    POSITIVE LOGITS
    æłĪ
    0.17
    StackSize
    0.14
     stack
    0.14
     Stack
    0.13
     stacking
    0.13
    STACK
    0.12
    _stack
    0.12
    _STACK
    0.12
    .Stack
    0.12
    -stack
    0.12
    Activations Density 0.175%

    No Known Activations