© 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. 13610
    Prev
    Next
    INDEX
    Explanations

    spiders and snakes

    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
    鸬
    -0.23
    èĨĺ
    -0.22
    åıĹæįŁ
    -0.20
    顽
    -0.20
    å«ĸ
    -0.19
    æ·«
    -0.19
    ä¸ĭæ²ī
    -0.19
    ritten
    -0.19
     repe
    -0.18
    (turn
    -0.18
    POSITIVE LOGITS
     venom
    0.28
    åį±éĻ©
    0.27
    ç§įç±»
    0.24
    å¨ģèĥģ
    0.23
     опаÑģ
    0.21
    åIJĵ
    0.21
     snakes
    0.21
    æģIJæĢĸ
    0.21
    åį±å®³
    0.21
    é«ĺæīĭ
    0.21
    Activations Density 0.023%

    No Known Activations