© 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. 16764
    Prev
    Next
    INDEX
    Explanations

    internal abbreviations

    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
    ะ
    -0.21
    åį¤
    -0.19
    ramid
    -0.19
    mer
    -0.18
    æľ¬ç½ij
    -0.18
    èľī
    -0.18
    ual
    -0.17
    ves
    -0.17
    to
    -0.17
    bon
    -0.17
    POSITIVE LOGITS
    illin
    0.21
    rypto
    0.20
    ircle
    0.20
    ramer
    0.19
    raft
    0.19
    IRCLE
    0.18
    rypt
    0.18
    ouncil
    0.18
    ircles
    0.18
    aching
    0.17
    Activations Density 0.199%

    No Known Activations