© 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. 14255
    Prev
    Next
    INDEX
    Explanations

    at last

    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
    utter
    -0.20
    sWith
    -0.20
    eing
    -0.18
    ething
    -0.17
    kip
    -0.17
    avers
    -0.17
    åħĴ
    -0.17
    pace
    -0.16
    bler
    -0.16
    åĦ¿
    -0.16
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.25
    shire
    0.20
    ments
    0.17
    ry
    0.15
    ment
    0.15
    ropy
    0.15
     Asi
    0.15
    tro
    0.15
    ly
    0.15
    èĩĥ
    0.15
    Activations Density 0.002%

    No Known Activations