© 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. 2458
    Prev
    Next
    INDEX
    Explanations

    comic book/movie titles

    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
     Witch
    -0.09
    å¿į
    -0.09
     pulver
    -0.09
    åħľ
    -0.08
    locks
    -0.08
    缣
    -0.08
    .gson
    -0.08
    견
    -0.08
    PIN
    -0.08
    lore
    -0.08
    POSITIVE LOGITS
    åĹ£
    0.10
     Mayer
    0.10
    udio
    0.09
    绿åŁİ
    0.09
    离å¼ĢäºĨ
    0.08
    ome
    0.08
    obre
    0.08
    obb
    0.08
    obby
    0.08
    salt
    0.08
    Activations Density 0.014%

    No Known Activations