© 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. 10093
    Prev
    Next
    INDEX
    Explanations

    Fort locations and fortifications

    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
    éĤ®å¯Ħ
    -0.11
    è¿Ľä¿®
    -0.10
    åī¯éĻ¢éķ¿
    -0.10
    çĥ¬
    -0.10
    soever
    -0.10
    loat
    -0.10
    éĻ¢éķ¿
    -0.10
    æľĢéķ¿
    -0.09
    å°½åĬĽ
    -0.09
    åĬĽäºī
    -0.09
    POSITIVE LOGITS
    bidden
    0.11
    åĿ»
    0.10
    èĩ¾
    0.10
    ament
    0.10
    aleza
    0.09
    ifications
    0.09
    ties
    0.09
    ened
    0.09
    bid
    0.09
    ady
    0.09
    Activations Density 0.016%

    No Known Activations