© 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. 63221
    Prev
    Next
    INDEX
    Explanations

    beginning and progression

    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
    åħį责声æĺİ
    -0.10
    istar
    -0.09
    ãģĽãģĦ
    -0.09
    them
    -0.08
    ой
    -0.08
    /high
    -0.08
    spe
    -0.08
    uten
    -0.08
    失æݧ
    -0.08
    ä¸ĢæĿ¡é¾Ļ
    -0.08
    POSITIVE LOGITS
    å·²ä¹ħçļĦ
    0.10
    ç½ijä¸Ĭ
    0.09
    iful
    0.09
    ä¹ĭæĹ¥èµ·
    0.09
    å·²ä¹ħ
    0.09
    ä¹ĭåĪĿ
    0.09
    OrUpdate
    0.09
    çĸļ
    0.08
    ively
    0.08
    nation
    0.08
    Activations Density 0.006%

    No Known Activations