© 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. 11168
    Prev
    Next
    INDEX
    Explanations

    geographically, geometrically, geological

    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
    nen
    -0.11
    çŃ·
    -0.11
    -produ
    -0.09
    lation
    -0.09
    tep
    -0.09
    erview
    -0.09
    ¿
    -0.09
    év
    -0.09
    åł
    -0.08
    umb
    -0.08
    POSITIVE LOGITS
    ALLY
    0.10
    ally
    0.10
    äºĪ
    0.10
    ically
    0.09
    ầ
    0.09
    0.09
    ometric
    0.08
    ographically
    0.08
    ãģ¦ãĤĤ
    0.08
    eful
    0.08
    Activations Density 0.026%

    No Known Activations