© 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. 17012
    Prev
    Next
    INDEX
    Explanations

    late+[temporal adjective/noun]

    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
    ย
    -0.10
    teenth
    -0.10
    nal
    -0.09
    Ñģлед
    -0.09
    new
    -0.09
     пеÑĢвÑĭй
    -0.09
    ยาว
    -0.09
    amel
    -0.09
    list
    -0.09
    teen
    -0.09
    POSITIVE LOGITS
    gers
    0.12
    itud
    0.12
    itudes
    0.11
    -stage
    0.11
    ño
    0.11
    -ish
    0.11
    ITUDE
    0.11
    leaf
    0.10
    -night
    0.10
    ices
    0.10
    Activations Density 0.032%

    No Known Activations