© 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. 5612
    Prev
    Next
    INDEX
    Explanations

    faction, radical, parties

    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
     realm
    -0.09
    æ¯ı人
    -0.09
    squeeze
    -0.08
    éĹ·
    -0.08
    çĨ
    -0.08
    页
    -0.08
    èµ°è¿ij
    -0.08
    _SHARED
    -0.08
    æµĴ
    -0.08
    Realm
    -0.08
    POSITIVE LOGITS
    åĬ¿åĬĽ
    0.13
    å°ijæķ°
    0.13
    åĬĽéĩı
    0.11
    åĪĨåŃIJ
    0.10
    åıį对
    0.10
    ises
    0.10
    åĨħéĥ¨
    0.10
    åij¨ä¸ī
    0.10
    个åĪ«
    0.10
    èŀ³
    0.10
    Activations Density 0.067%

    No Known Activations