© 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. 10851
    Prev
    Next
    INDEX
    Explanations

    specific punctuation and characters

    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
    rem
    -0.22
    plex
    -0.21
    udev
    -0.20
    par
    -0.20
    REM
    -0.20
     rem
    -0.20
    Rem
    -0.20
    boro
    -0.20
     leftover
    -0.19
    Gear
    -0.18
    POSITIVE LOGITS
    anke
    0.24
    æ¡ĥ
    0.21
    纨
    0.20
    ä¹ĭ声
    0.19
    anta
    0.18
     Leigh
    0.18
     RETURNS
    0.18
    SingleNode
    0.18
    ictim
    0.17
    /packages
    0.17
    Activations Density 0.067%

    No Known Activations