© 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. 14013
    Prev
    Next
    INDEX
    Explanations

    starting point or beginning

    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
    æľºæŀĦ
    -0.20
    第ä¸ī代
    -0.20
    åį¿
    -0.19
    çī¹æ®Ĭ
    -0.19
    ed
    -0.19
     dodge
    -0.18
    rels
    -0.18
    ä½ĵç³»
    -0.17
     parallel
    -0.17
    åħ±æľī
    -0.17
    POSITIVE LOGITS
    第ä¸ĢæŃ¥
    0.24
    åģļèµ·
    0.23
    èµ·çĤ¹
    0.23
    /start
    0.21
    è®®
    0.20
    :start
    0.20
    çĿĢæīĭ
    0.20
    æĭĽåij¼
    0.20
     conversations
    0.20
    ë¶ĢíĦ°
    0.19
    Activations Density 0.036%

    No Known Activations