© 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. 4655
    Prev
    Next
    INDEX
    Explanations

    going through

    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
    ãĤªãĥ³
    -0.10
    åIJĮå¿Ĺ们
    -0.10
    çIJħ
    -0.10
    åĪĹåħ¥
    -0.09
    caps
    -0.09
    æ¦ľ
    -0.09
    deb
    -0.09
    ä¸Ģæīĭ
    -0.09
    èĪĴ
    -0.08
    combe
    -0.08
    POSITIVE LOGITS
    ÑĤем
    0.09
    ä»Ģä¹Īåı«
    0.08
     Parad
    0.08
    éĿĴæĺ¥æľŁ
    0.08
    ienie
    0.08
    å·«
    0.08
     hoops
    0.08
    ä¸Ģéĺµ
    0.08
    åIJĮæł·çļĦ
    0.08
    _skb
    0.07
    Activations Density 0.010%

    No Known Activations