© 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. 31306
    Prev
    Next
    INDEX
    Explanations

    metal bands and related entities

    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
    è§Į
    -0.11
    Ñıд
    -0.10
    es
    -0.10
    onz
    -0.09
    er
    -0.09
    nable
    -0.09
    sa
    -0.08
    etz
    -0.08
    ãģ¹ãģį
    -0.08
    emie
    -0.08
    POSITIVE LOGITS
    licity
    0.18
    lica
    0.15
    ized
    0.13
    ted
    0.12
    lify
    0.11
    ters
    0.11
    working
    0.10
    ulous
    0.10
    ctic
    0.10
    å±ij
    0.10
    Activations Density 0.033%

    No Known Activations