© 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. 19174
    Prev
    Next
    INDEX
    Explanations

    title tracks, theme songs, opening scenes, species

    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
    æ·±å¤Ħ
    -0.09
    BITS
    -0.09
     Marian
    -0.08
    éļıæŶ
    -0.08
    lug
    -0.08
     Thornton
    -0.08
    è°²
    -0.08
    íĤ¹
    -0.08
    ĺ
    -0.08
    åħĪçĶŁ
    -0.08
    POSITIVE LOGITS
    ä¹ĭä¸Ģ
    0.10
    eti
    0.10
    agnar
    0.09
    大æĸ¹
    0.09
    /Main
    0.09
    å«ĸ
    0.09
    /operator
    0.09
    /main
    0.08
     Killer
    0.08
    etrize
    0.08
    Activations Density 0.060%

    No Known Activations