© 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. 17589
    Prev
    Next
    INDEX
    Explanations

    statement of belief or hypothesis

    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
    è¿«
    -0.09
    çĴŀ
    -0.08
    éĨĴ
    -0.08
    ç¹ģ
    -0.08
    åIJ¦
    -0.08
    ALA
    -0.08
    agedList
    -0.08
    éĢļçŁ¥ä¹¦
    -0.08
    avr
    -0.08
    uant
    -0.08
    POSITIVE LOGITS
     rằng
    0.18
     bahwa
    0.16
     hogy
    0.12
     بأÙĨ
    0.10
     ÑĩÑĤо
    0.10
    fact
    0.10
     että
    0.10
     że
    0.10
     that
    0.09
    that
    0.09
    Activations Density 0.122%

    No Known Activations