© 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. 10933
    Prev
    Next
    INDEX
    Explanations

    dialing, dialer, dial tone

    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
     sÃłng
    -0.17
     ÙĪاÙĦØŃ
    -0.16
    stype
    -0.16
    _trial
    -0.16
    -wife
    -0.16
    дей
    -0.16
    visa
    -0.16
    ideo
    -0.15
    idue
    -0.15
    chw
    -0.15
    POSITIVE LOGITS
    er
    0.27
    ysis
    0.20
    å¾Ĺèµ·
    0.19
    ling
    0.18
    ables
    0.18
    å¾Ĺå¾Ī
    0.18
    rand
    0.17
    -out
    0.17
    ers
    0.17
    ا
    0.17
    Activations Density 0.015%

    No Known Activations