© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12558
    Prev
    Next
    INDEX
    Explanations

    smell or scent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    æĢģ
    -0.19
    çīĩåŃIJ
    -0.19
    atty
    -0.18
    çµ®
    -0.17
    edly
    -0.17
    imiento
    -0.17
    ayment
    -0.17
    é«»
    -0.17
    $form
    -0.17
    è§Ĩè§Ĵ
    -0.17
    POSITIVE LOGITS
     smells
    0.22
     unfamiliar
    0.22
     smoke
    0.21
     smelling
    0.20
    åı¯çĸij
    0.20
    gg
    0.20
     smell
    0.20
    ä¸ĢèĤ¡
    0.19
    æ°Ķæģ¯
    0.19
    çĨı
    0.18
    Activations Density 0.021%

    No Known Activations