© 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. 50334
    Prev
    Next
    INDEX
    Explanations

    addresses and location codes

    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
    äºĨ解
    -0.09
    FORM
    -0.08
    毫ä¸į
    -0.07
    çĶ¦
    -0.07
    è¿Ļ个è¯į
    -0.07
    æŀģåĬĽ
    -0.07
    ASM
    -0.07
    ERE
    -0.07
    SMS
    -0.07
    çī¢
    -0.07
    POSITIVE LOGITS
    ftware
    0.10
    箾
    0.09
    è¾£
    0.09
    ä¿İ
    0.09
    å¯ĵ
    0.09
    eters
    0.09
    çĵ¯
    0.09
    模èĮĥ
    0.09
    ditor
    0.09
    apper
    0.09
    Activations Density 0.015%

    No Known Activations