© 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. 6309
    Prev
    Next
    INDEX
    Explanations

    Resident Evil, Stranger Things, Capcom, Myers

    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
    entities
    -0.09
    ophon
    -0.09
    å®ŀä½ĵ
    -0.09
    士
    -0.08
    SPELL
    -0.08
    SED
    -0.08
    èĭı
    -0.08
     duel
    -0.08
    åĬłå¯Ĩ
    -0.08
    å¯Ĩå°ģ
    -0.08
    POSITIVE LOGITS
    èĭĶ
    0.10
    åij¨åĽ´çļĦ
    0.09
    æīĵæī«
    0.09
    æ´»ä¸ĭåİ»
    0.09
    æIJı
    0.09
    éĻĦè¿ijçļĦ
    0.09
    æįĨç»ij
    0.09
    è¿ĺæľīä¸ĢäºĽ
    0.09
    åīįæīĢ
    0.09
    çĽĺæ´»
    0.09
    Activations Density 0.022%

    No Known Activations