© 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. 32213
    Prev
    Next
    INDEX
    Explanations

    amongst other

    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
    sand
    -0.09
    éĵĽ
    -0.09
    ä¸įæŃ»
    -0.08
    ä¸įå®ľ
    -0.08
    æģķ
    -0.08
    бÑĢо
    -0.08
    eree
    -0.08
    ukt
    -0.08
    inct
    -0.08
    ä¸įçĶ¨
    -0.08
    POSITIVE LOGITS
    ä»Ģä¹Īéĥ½
    0.13
     anything
    0.13
     things
    0.11
     thing
    0.11
    anything
    0.10
    äºĭåĦ¿
    0.10
    åħ¶å®ĥéĹ®é¢ĺ
    0.10
    åħ¶ä»ĸçļĦ
    0.10
    Anything
    0.10
    اÙħر
    0.10
    Activations Density 0.042%

    No Known Activations