© 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. 49232
    Prev
    Next
    INDEX
    Explanations

    supply zone

    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
    è§Ħå¾ĭ
    -0.09
    tá
    -0.09
    AdapterManager
    -0.09
    è®°
    -0.09
    uos
    -0.09
     Thảo
    -0.09
     вÑĭгод
    -0.08
    çĶ¨è½¦
    -0.08
    IGH
    -0.08
     Holmes
    -0.08
    POSITIVE LOGITS
    assa
    0.10
    å®ī举
    0.09
    æŃ¢
    0.09
    个èĤ¡
    0.08
    å½¢æĢģ
    0.08
    追踪
    0.08
    æīĭåĬ¿
    0.08
    ä¸īä½į
    0.08
    robat
    0.08
     ls
    0.08
    Activations Density 0.069%

    No Known Activations