© 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. 31301
    Prev
    Next
    INDEX
    Explanations

    one to one

    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
    åIJĿ
    -0.10
    ä¸ĭåįĬ
    -0.10
    .sig
    -0.09
    éŀŃ
    -0.09
    é¢ĨæĤŁ
    -0.09
    çĦī
    -0.09
    åħģ许
    -0.08
    ç»ĻåĬĽ
    -0.08
    itim
    -0.08
    езд
    -0.08
    POSITIVE LOGITS
     exact
    0.15
    ãģĿãģ®ãģ¾ãģ¾
    0.13
    ä¸Ģä¸Ģ
    0.13
    exact
    0.13
     exactly
    0.12
    ä¸Ģ对ä¸Ģ
    0.12
    åİŁ
    0.11
    å®Įåħ¨
    0.11
     Exact
    0.11
    Exact
    0.11
    Activations Density 0.086%

    No Known Activations