© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20642
    Prev
    Next
    INDEX
    Explanations

    hypothetical conditions with "would be"

    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
    rete
    -0.11
    arer
    -0.09
    orio
    -0.09
    auf
    -0.08
    .asp
    -0.08
    onaut
    -0.08
    PropertyDescriptor
    -0.08
    neau
    -0.08
    conciliation
    -0.08
    ä¸ĢæĬ¹
    -0.08
    POSITIVE LOGITS
    åĽºçĦ¶
    0.10
    æŶè£ħ
    0.09
    eneg
    0.09
    æľī两ç§į
    0.08
    端æŃ£
    0.08
    åĿı
    0.08
    磮
    0.08
    din
    0.08
    onders
    0.08
    èĮ¬
    0.08
    Activations Density 0.107%

    No Known Activations