© 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. 18359
    Prev
    Next
    INDEX
    Explanations

    hero or martyr figures

    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
    åѦä¼ļ
    -0.10
     fr
    -0.10
    çĪ±å¥½
    -0.09
    å¯Į
    -0.09
    åij
    -0.08
    æ½Ń
    -0.08
    åħ´è¶£
    -0.08
    éĻIJæľŁ
    -0.08
     Fr
    -0.08
    åĽĽåŃ£
    -0.08
    POSITIVE LOGITS
    èĭ±éĽĦ
    0.26
     hero
    0.22
     heroes
    0.22
    hero
    0.20
    heroes
    0.19
    -hero
    0.18
     геÑĢо
    0.17
    Heroes
    0.17
    (hero
    0.16
    .hero
    0.16
    Activations Density 0.099%

    No Known Activations