© 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. 33697
    Prev
    Next
    INDEX
    Explanations

    films and documentaries

    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
    ulum
    -0.09
    ait
    -0.08
    订
    -0.08
    èļ°
    -0.08
    ultimate
    -0.08
    andr
    -0.08
     Rec
    -0.08
    .bc
    -0.08
     struck
    -0.08
    å¿ĥ头
    -0.08
    POSITIVE LOGITS
    åħ³éĹŃ
    0.10
    çıī
    0.09
    ç§ķ
    0.09
    movies
    0.09
    æī¹ç¤º
    0.09
    _interest
    0.09
    cpp
    0.09
    å½±
    0.09
    phy
    0.09
    继æī¿
    0.09
    Activations Density 0.205%

    No Known Activations