© 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. 11183
    Prev
    Next
    INDEX
    Explanations

    acoustic guitar songs

    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
    åŁ¼
    -0.10
    骧
    -0.09
    zÅij
    -0.09
    çļĦç¡®
    -0.09
    бег
    -0.09
    å£ķ
    -0.09
    å§IJ妹
    -0.08
     Abb
    -0.08
    anine
    -0.08
    itia
    -0.08
    POSITIVE LOGITS
    åIJīä»ĸ
    0.13
     guitar
    0.11
     guitars
    0.11
     wed
    0.10
    éĵ®
    0.10
    客æłĪ
    0.09
     wedge
    0.09
    engu
    0.09
    çIJ´
    0.09
    èĥĮåĮħ
    0.09
    Activations Density 0.256%

    No Known Activations