© 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. 12463
    Prev
    Next
    INDEX
    Explanations

    horn

    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
    Ñħод
    -0.20
    TING
    -0.18
    urnal
    -0.18
    apons
    -0.16
    ient
    -0.16
    æ¸į
    -0.15
    amodel
    -0.15
    ij
    -0.15
    sst
    -0.15
    ãģĦãģĨ
    -0.14
    POSITIVE LOGITS
    less
    0.25
    lessly
    0.25
    /or
    0.19
    egg
    0.17
    berger
    0.17
    inals
    0.17
    uckle
    0.17
    LESS
    0.17
    OfDay
    0.16
    åľ°å¸¦
    0.16
    Activations Density 0.008%

    No Known Activations