© 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. 11149
    Prev
    Next
    INDEX
    Explanations

    directions toward or towards

    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
    zione
    -0.19
     поÑģколÑĮ
    -0.19
    zzle
    -0.17
    oen
    -0.17
    rame
    -0.17
    èIJ½ãģ¡
    -0.17
    缸å½ĵäºİ
    -0.17
     ÐĶмиÑĤÑĢ
    -0.17
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.17
    å½ĵä»ĸ
    -0.16
    POSITIVE LOGITS
    /from
    0.30
    gether
    0.25
    /out
    0.22
    /on
    0.21
    éļħ
    0.21
    /about
    0.20
    /down
    0.19
    /at
    0.19
    /by
    0.19
    ships
    0.18
    Activations Density 0.017%

    No Known Activations