© 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. 12910
    Prev
    Next
    INDEX
    Explanations

    cyanobacteria and algae

    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
    (inertia
    -0.22
    åĿĩ使åħ¶
    -0.21
    çĨ¨
    -0.20
    è½´æī¿
    -0.19
    çīµå¼ķ
    -0.19
    çĤİçĹĩ
    -0.18
    á´¼
    -0.18
    æīĭæľ¯
    -0.18
    éĿ´
    -0.18
    èħ¿éĥ¨
    -0.18
    POSITIVE LOGITS
     algae
    0.23
    èĹ»
    0.22
     bri
    0.21
    èĭĶ
    0.21
    /lic
    0.20
    èĥŀ
    0.20
    æ¼Ķ
    0.20
    gó
    0.20
    ç»¿åľ°
    0.20
    èĹĵ
    0.20
    Activations Density 0.046%

    No Known Activations