© 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. 13183
    Prev
    Next
    INDEX
    Explanations

    jet black

    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
    æĻ°
    -0.19
    æĸ¯åŁº
    -0.17
    аÑĪ
    -0.15
    orr
    -0.15
    _PCIE
    -0.15
    addon
    -0.15
    ount
    -0.14
    pir
    -0.14
    ench
    -0.14
    junction
    -0.14
    POSITIVE LOGITS
    lify
    0.26
    ting
    0.25
    ted
    0.24
    tings
    0.24
    ty
    0.19
    ters
    0.18
    preter
    0.18
    anic
    0.18
    aneous
    0.18
    çĦ¶æĺ¯
    0.18
    Activations Density 0.010%

    No Known Activations