© 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. 56853
    Prev
    Next
    INDEX
    Explanations

    physical and tangible items

    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
     Eh
    -0.11
    .descriptor
    -0.10
    _FRE
    -0.09
    侦
    -0.09
    alley
    -0.09
    stroy
    -0.09
    ×ķ׳×Ļ×Ŀ
    -0.09
    娥
    -0.09
    裤
    -0.08
    驼
    -0.08
    POSITIVE LOGITS
    å®ŀçī©
    0.20
    å®ŀä½ĵ
    0.17
     tangible
    0.15
     physical
    0.13
    physical
    0.12
    Physical
    0.12
     concrete
    0.11
    æĪIJåĵģ
    0.11
     Physical
    0.11
    çī©åĵģ
    0.11
    Activations Density 0.097%

    No Known Activations