© 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. 9834
    Prev
    Next
    INDEX
    Explanations

    legal terms and conditions

    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
    侪
    -0.09
    heim
    -0.09
    kir
    -0.09
    æŬ
    -0.08
    atto
    -0.08
    .quality
    -0.08
    urs
    -0.08
    jit
    -0.08
     PARTY
    -0.08
    tin
    -0.07
    POSITIVE LOGITS
    /legal
    0.13
    åIJĪè§Ħ
    0.12
    åIJĪæ³ķ
    0.12
    usercontent
    0.10
    æı´åĬ©
    0.10
    ább
    0.10
    /il
    0.09
    -minded
    0.09
    mente
    0.09
    åIJĪæ³ķæĢ§
    0.09
    Activations Density 0.063%

    No Known Activations