© 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. 22256
    Prev
    Next
    INDEX
    Explanations

    "the " followed by titles

    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
    ķ
    -0.09
    çĶļ
    -0.08
    inus
    -0.08
    lah
    -0.08
    orno
    -0.08
    ierte
    -0.08
    doc
    -0.08
    è·ĭ
    -0.08
     stark
    -0.08
    enerated
    -0.07
    POSITIVE LOGITS
    orem
    0.14
    oretical
    0.13
    ories
    0.12
    olog
    0.11
    odor
    0.10
    оÑģÑĮ
    0.10
    ft
    0.10
    ater
    0.10
    ological
    0.10
    orie
    0.10
    Activations Density 0.081%

    No Known Activations