© 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. 26874
    Prev
    Next
    INDEX
    Explanations

    mo + positive 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
    ä¸Ģå¥Ĺ
    -0.08
    å½ĵå¹´
    -0.08
    upt
    -0.08
    ourn
    -0.08
    ners
    -0.08
    æݨçIJĨ
    -0.08
    ä¸Ģé¦ĸ
    -0.08
    çĥ¬
    -0.08
    furt
    -0.08
    ruk
    -0.08
    POSITIVE LOGITS
    山寨
    0.10
    åĮ¹
    0.10
    isson
    0.10
    çľĭ书
    0.10
    oring
    0.09
    èµ·ä¹ī
    0.09
    رض
    0.08
    åĽ½æĥħ
    0.08
    çŁ¥ä¹İ
    0.08
    èµĶ
    0.08
    Activations Density 0.024%

    No Known Activations