© 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. 35802
    Prev
    Next
    INDEX
    Explanations

    agree with, mentioned, commenting

    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
    7
    -0.09
    æģ©
    -0.09
    5
    -0.08
    è¿IJä½ľ
    -0.08
    4
    -0.08
    ENE
    -0.08
    1
    -0.08
     sept
    -0.08
    2
    -0.08
    6
    -0.08
    POSITIVE LOGITS
    asad
    0.12
    æİĩ
    0.10
    祯
    0.10
    楼ä¸Ĭ
    0.10
    çĤ¹å¤´
    0.10
    SHOT
    0.09
    æ¡¢
    0.09
    佯
    0.09
    éĺµéĺµ
    0.09
    æijĩ头
    0.09
    Activations Density 0.029%

    No Known Activations