© 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. 22709
    Prev
    Next
    INDEX
    Explanations

    through situations

    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
    occer
    -0.09
    UCH
    -0.09
    稷
    -0.09
    iad
    -0.09
    hart
    -0.08
    curring
    -0.08
    aturing
    -0.08
    ÙĪØ«
    -0.08
    çĨĦ
    -0.08
    spot
    -0.08
    POSITIVE LOGITS
    åĪĿæģĭ
    0.09
    éļ¾åħ³
    0.09
     Heath
    0.09
    èij³
    0.09
    è¿ĻäºĽä¸ľè¥¿
    0.09
    æīĢåģļçļĦ
    0.08
    人æīį
    0.08
    åŃļ
    0.08
     Eg
    0.08
    æĬ¹
    0.08
    Activations Density 0.014%

    No Known Activations