© 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. 19763
    Prev
    Next
    INDEX
    Explanations

    granular

    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
    ETY
    -0.12
    åłª
    -0.09
    arty
    -0.09
    CBS
    -0.09
    æ¶ĪåĮĸ
    -0.09
    å´¤
    -0.09
    éli
    -0.08
    ä¸ºæł¸å¿ĥçļĦ
    -0.08
    åĬŀäºĭå¤Ħ
    -0.08
    .untracked
    -0.08
    POSITIVE LOGITS
    aber
    0.09
    éĺľ
    0.09
    kı
    0.08
    å·´æĭī
    0.08
     Mater
    0.08
    emet
    0.08
     matter
    0.08
    tempts
    0.08
    Bridge
    0.08
    empo
    0.08
    Activations Density 0.006%

    No Known Activations