© 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. 15657
    Prev
    Next
    INDEX
    Explanations

    Salem and Saul

    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
    itional
    -0.20
    ola
    -0.19
    æĪĸå¤ļ
    -0.18
    ials
    -0.18
    ity
    -0.18
    idad
    -0.18
    çĮĹ
    -0.17
    oke
    -0.17
    ../../
    -0.17
    istic
    -0.17
    POSITIVE LOGITS
    0.26
    oppel
    0.21
    ÙĦÙĥ
    0.16
    ftware
    0.15
    éĤ¾
    0.15
    åķĨ家
    0.15
    atters
    0.15
    ppers
    0.15
    warf
    0.15
    INATION
    0.15
    Activations Density 0.001%

    No Known Activations