© 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. 58595
    Prev
    Next
    INDEX
    Explanations

    email addresses or author info

    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
    çIJĽ
    -0.09
    rd
    -0.09
    çĶµç«Ļ
    -0.08
    åĩĨ
    -0.08
    èī°
    -0.08
    ilde
    -0.08
     alive
    -0.08
    åľ¨æĹ¥æľ¬
    -0.08
    operation
    -0.08
    鸱
    -0.08
    POSITIVE LOGITS
    é»į
    0.11
    ajas
    0.09
    ä¿į
    0.09
    ëį°ìĿ´
    0.09
    ¦
    0.09
    å¥ĩå¼Ĥ
    0.09
    PIP
    0.09
    MMdd
    0.09
    LLU
    0.09
    pread
    0.09
    Activations Density 0.002%

    No Known Activations