© 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. 15381
    Prev
    Next
    INDEX
    Explanations

    length of

    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
    ategory
    -0.15
     nhiêu
    -0.15
    اÙĥ
    -0.15
    ðŁı»
    -0.15
    -ended
    -0.15
    çĽĶ
    -0.15
    otos
    -0.15
    ContentLoaded
    -0.15
     каÑĩеÑģÑĤва
    -0.14
     налиÑĩии
    -0.14
    POSITIVE LOGITS
    ening
    0.27
    wise
    0.26
    ened
    0.26
    mate
    0.23
    icals
    0.20
    ieu
    0.19
    OfDay
    0.18
    mu
    0.18
    mates
    0.18
    aho
    0.18
    Activations Density 0.047%

    No Known Activations