© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 21837
    Prev
    Next
    INDEX
    Explanations

    allies, alliances, confederations, organizations, powers, axis, league, secretary

    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
    íİĮ
    -0.10
    çĹ«
    -0.10
     Hud
    -0.09
    éªĩ
    -0.09
    å®ī康
    -0.09
    示èĮĥåŁºåľ°
    -0.09
    _scaling
    -0.08
    乡æĿij
    -0.08
    äºĮ人
    -0.08
    åīĶ
    -0.08
    POSITIVE LOGITS
    èģĶ缣
    0.13
    缣
    0.13
    åĬłçĽŁ
    0.11
    æĪIJåijĺåĽ½
    0.11
    诸侯
    0.10
     alliance
    0.10
    èģĶåIJĪ
    0.10
     League
    0.09
    åħ¬çº¦
    0.09
    çIJĨäºĭä¼ļ
    0.09
    Activations Density 0.085%

    No Known Activations