© 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. 12389
    Prev
    Next
    INDEX
    Explanations

    your access payment health

    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
     panicked
    -0.21
    onde
    -0.20
    综åIJĪæĢ§
    -0.19
    empt
    -0.19
    anc
    -0.18
    hat
    -0.18
    borg
    -0.18
     CAPITAL
    -0.18
    -Feb
    -0.18
    åħ¼
    -0.18
    POSITIVE LOGITS
    éĢįéģ¥
    0.21
    .SC
    0.20
    èıľ
    0.20
    å½ĵä½ł
    0.20
    _ub
    0.19
    å§Ķç»Ħç»ĩ
    0.19
    çīĪ
    0.19
     METHODS
    0.19
     Preston
    0.19
    enames
    0.19
    Activations Density 0.440%

    No Known Activations