© 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. 12557
    Prev
    Next
    INDEX
    Explanations

    express or

    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
    entifier
    -0.21
    yards
    -0.20
    ê¹IJ
    -0.19
    sters
    -0.19
    edException
    -0.17
     constexpr
    -0.17
    bage
    -0.16
    åĩºçīĪ社
    -0.16
    abal
    -0.15
    IGATION
    -0.15
    POSITIVE LOGITS
    ively
    0.33
    iveness
    0.26
    ional
    0.21
    nel
    0.20
    ives
    0.19
     Ñģобой
    0.19
    主ä¹ī
    0.18
    ions
    0.17
    ion
    0.17
    ive
    0.17
    Activations Density 0.068%

    No Known Activations