© 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. 33451
    Prev
    Next
    INDEX
    Explanations

    enough followed by a noun

    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
    ry
    -0.10
    ÙĥØ©
    -0.10
    -era
    -0.09
    izations
    -0.09
    èĭ¥å¹²
    -0.09
    ä¸Ģ声
    -0.09
    utton
    -0.09
    ä½ķå¤Ħ
    -0.08
    too
    -0.08
    ssue
    -0.08
    POSITIVE LOGITS
    /all
    0.12
    urator
    0.11
    ìĶ©
    0.11
    ä¸ľè¥¿
    0.10
    elsen
    0.10
    å¹´åīį
    0.10
    est
    0.09
    ayar
    0.09
    é»ĺå¥ij
    0.09
     darn
    0.09
    Activations Density 0.017%

    No Known Activations