© 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. 12226
    Prev
    Next
    INDEX
    Explanations

    chronological time

    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
    ëģĶ
    -0.21
    --------------------------------------------------------------------------↵
    -0.18
    ters
    -0.18
    ðŁı»
    -0.18
    ween
    -0.16
    teenth
    -0.16
    ted
    -0.16
    ilon
    -0.16
    èķĪ
    -0.15
    room
    -0.15
    POSITIVE LOGITS
    以ä¾Ĩ
    0.18
    ãĤĤãģĨ
    0.17
    usz
    0.17
    mute
    0.16
    aise
    0.16
    odic
    0.16
    ships
    0.15
    le
    0.15
    afen
    0.15
    um
    0.15
    Activations Density 0.014%

    No Known Activations