© 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. 3809
    Prev
    Next
    INDEX
    Explanations

    coming home

    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
    çķĻåľ¨
    -0.08
    esen
    -0.08
    سب
    -0.08
    åĨħéĻĨ
    -0.08
    ç¾İå¾·
    -0.08
    .psi
    -0.08
    à¹ģละà¸Ħวาม
    -0.08
    ennen
    -0.08
    æĦŁåĬ¨
    -0.08
    .rmi
    -0.08
    POSITIVE LOGITS
    wards
    0.12
    ward
    0.10
    éĢĶ
    0.09
    liers
    0.09
    å±¥èģĮ
    0.09
    WARDS
    0.09
    æľīç§į
    0.09
    WARD
    0.09
    éĢĶä¸Ń
    0.09
    çĵ¶é¢Ī
    0.08
    Activations Density 0.011%

    No Known Activations