© 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. 57763
    Prev
    Next
    INDEX
    Explanations

    pump

    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
    ãģĦãģĨ
    -0.09
    semb
    -0.09
    Äĥng
    -0.09
     einf
    -0.08
    ANCE
    -0.08
    ented
    -0.08
    amax
    -0.08
    ntax
    -0.08
    EMENT
    -0.08
    å·¡èĪª
    -0.08
    POSITIVE LOGITS
    kins
    0.13
    elling
    0.11
    enzie
    0.10
    arine
    0.10
    ers
    0.10
    soever
    0.09
    unu
    0.09
     reap
    0.09
    eurs
    0.09
    åĢĮ
    0.09
    Activations Density 0.018%

    No Known Activations