© 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. 14368
    Prev
    Next
    INDEX
    Explanations

    override methods

    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
    称ä¹ĭ
    -0.21
    ä¸įèī¯
    -0.19
    æŃ£åĵģ
    -0.18
    å®Įç¾İ
    -0.18
    æİĴ污
    -0.18
    èĩªæķij
    -0.18
    RG
    -0.17
    _ment
    -0.17
    ARG
    -0.17
    Pad
    -0.17
    POSITIVE LOGITS
    ylon
    0.23
    æīĵå¼ĢäºĨ
    0.20
    åįģåĪĨéĴŁ
    0.19
     Cornel
    0.18
    ä¼ĺåħĪ
    0.18
     mach
    0.18
    åħīæ³½
    0.17
    ä¼ŀ
    0.17
     mut
    0.17
    flare
    0.17
    Activations Density 0.012%

    No Known Activations