© 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. 31767
    Prev
    Next
    INDEX
    Explanations

    up and running

    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
    éĵ¶æ²³
    -0.11
    amus
    -0.09
    fare
    -0.09
    _REQUIRE
    -0.09
    OwnProperty
    -0.09
    交åıī
    -0.09
    arium
    -0.08
    sert
    -0.08
     bÄĻd
    -0.08
     kommer
    -0.08
    POSITIVE LOGITS
    平稳
    0.11
    å®ī稳
    0.10
    å¿«éĢŁ
    0.09
    导åIJij
    0.09
    稳å®ļ
    0.08
    ze
    0.08
    å®īå¿ĥ
    0.08
    æľĢçµĤ
    0.08
    æĬķåħ¥ä½¿çĶ¨
    0.08
    orientation
    0.08
    Activations Density 0.077%

    No Known Activations