© 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. 33186
    Prev
    Next
    INDEX
    Explanations

    compound words and phrases

    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
    estate
    -0.09
    ابر
    -0.09
    qid
    -0.09
    ÑĦа
    -0.09
    CallCheck
    -0.08
    ç¦Ģ
    -0.08
     Ellison
    -0.08
    çĤľ
    -0.08
    LObject
    -0.08
    itable
    -0.08
    POSITIVE LOGITS
    æķĪåºĶ
    0.11
    ä¸Ģå±Ĥ
    0.10
    åħ³åĪĩ
    0.09
    å¹´å¤ľ
    0.09
    æĥ³æī¾
    0.09
    å¤ĸå¢Ļ
    0.09
     efforts
    0.09
    è¿
    0.09
    unt
    0.09
     effect
    0.09
    Activations Density 0.026%

    No Known Activations