© 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. 22149
    Prev
    Next
    INDEX
    Explanations

    progenitor/progeny and postal codes

    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
    lle
    -0.09
    sc
    -0.09
    de
    -0.09
    ism
    -0.09
    eller
    -0.08
    set
    -0.08
    ified
    -0.08
    ers
    -0.08
    à¹Į
    -0.08
     лиÑĪ
    -0.08
    POSITIVE LOGITS
    holm
    0.10
    forth
    0.09
    å·²ä¹ħçļĦ
    0.09
    hole
    0.09
    iert
    0.09
    itional
    0.09
    onal
    0.09
    çĦ¦
    0.09
    viron
    0.09
    alars
    0.09
    Activations Density 0.143%

    No Known Activations