© 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. 33247
    Prev
    Next
    INDEX
    Explanations

    wood-related place names

    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
    ëģĶ
    -0.14
    oire
    -0.12
    ãģįãģ¦
    -0.11
    odium
    -0.10
    ãģįãģ¡ãĤĵãģ¨
    -0.10
    andro
    -0.09
    ãĤĤãģ£ãģ¨
    -0.09
    ifo
    -0.09
    ions
    -0.09
    Ĵ
    -0.09
    POSITIVE LOGITS
    iness
    0.14
    ering
    0.12
    ness
    0.11
    èĩ¾
    0.11
    ier
    0.11
    esign
    0.10
    side
    0.10
    ered
    0.10
    erness
    0.10
    樨
    0.10
    Activations Density 0.032%

    No Known Activations