© 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. 37687
    Prev
    Next
    INDEX
    Explanations

    move between things

    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
    izz
    -0.11
    ries
    -0.10
    inz
    -0.09
    mut
    -0.09
    mage
    -0.09
    ented
    -0.09
    æĮ¹
    -0.09
    nut
    -0.09
    utz
    -0.09
     вÑģÑı
    -0.09
    POSITIVE LOGITS
    overs
    0.10
    èĩªå¦Ĥ
    0.10
    åĴĮå®ĮåĸĦ
    0.10
    tures
    0.09
     Petit
    0.09
    /stretch
    0.09
    estre
    0.09
    uire
    0.08
    fuscated
    0.08
    able
    0.08
    Activations Density 0.080%

    No Known Activations