© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16164
    Prev
    Next
    INDEX
    Explanations

    U.S

    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
    nya
    -0.33
    ness
    -0.26
    no
    -0.25
    ni
    -0.24
    s
    -0.23
    na
    -0.23
    net
    -0.23
    not
    -0.22
    ened
    -0.22
    nt
    -0.21
    POSITIVE LOGITS
    ropa
    0.23
    à¸ĵ
    0.23
    pton
    0.22
    prising
    0.22
    nder
    0.21
    psilon
    0.21
    çĴł
    0.20
    clidean
    0.20
    eing
    0.19
    kraine
    0.19
    Activations Density 0.098%

    No Known Activations