© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51060
    Prev
    Next
    INDEX
    Explanations

    risk and assessment

    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
    pit
    -0.09
     Pitt
    -0.09
    itra
    -0.09
    çħ§
    -0.09
     PIT
    -0.09
     Bett
    -0.08
    ultipart
    -0.08
    寡
    -0.08
    enda
    -0.08
    bir
    -0.08
    POSITIVE LOGITS
    é£İéĻ©
    0.21
    風éļª
    0.17
    é£İéĻ©ç®¡çIJĨ
    0.17
     risk
    0.17
     Risk
    0.17
    Risk
    0.16
    çļĦé£İéĻ©
    0.16
    risk
    0.15
    ãĥªãĤ¹ãĤ¯
    0.15
     risks
    0.14
    Activations Density 0.096%

    No Known Activations