© 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. 37808
    Prev
    Next
    INDEX
    Explanations

    checkboxes and ticking

    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
    orf
    -0.09
    arya
    -0.09
     Jam
    -0.09
    .fromString
    -0.09
    åį·
    -0.08
    rops
    -0.08
    é²ĩ
    -0.08
    attering
    -0.08
    DMI
    -0.08
    ëį°
    -0.08
    POSITIVE LOGITS
     tick
    0.09
    tick
    0.09
    .isChecked
    0.09
    ANC
    0.09
    è´²
    0.09
    æĤ¬æµ®
    0.09
    ãĥ¼ãĥ«
    0.09
    é¹Ħ
    0.08
    çĹķ
    0.08
    è·Łè¸ª
    0.08
    Activations Density 0.087%

    No Known Activations