© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10195
    Prev
    Next
    INDEX
    Explanations

    go + preposition/adverb

    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
    ivic
    -0.12
    opper
    -0.09
    ially
    -0.09
    å±Ģéķ¿
    -0.09
    åŃº
    -0.09
    .sap
    -0.09
    æŶèĬĤ
    -0.09
    vant
    -0.09
     ward
    -0.09
    urch
    -0.09
    POSITIVE LOGITS
    åij¨åĪĬ
    0.09
    nob
    0.09
    èµŀ
    0.09
    AuthProvider
    0.09
    gren
    0.08
    èĦ±ç¦»
    0.08
    ç¿ĺ
    0.08
     out
    0.08
    æĬĬä»ĸ
    0.08
     discreet
    0.08
    Activations Density 0.052%

    No Known Activations