© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17383
    Prev
    Next
    INDEX
    Explanations

    side effects or complications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    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
    ×ijת
    -0.06
    pte
    -0.06
    etto
    -0.06
    ä¸ĭä¸Ģ个
    -0.06
     full
    -0.06
    orks
    -0.06
    æĪijä¸įæķ¢
    -0.06
    ãĥķãĤ©ãĥ¼ãĥł
    -0.06
    kow
    -0.06
    éĢĤåIJĪçļĦ
    -0.05
    POSITIVE LOGITS
    åĪĿ
    0.06
    rench
    0.05
    çļĦç¨ĭ度
    0.05
    å®ļ
    0.05
     indisc
    0.05
    æĻºèĢħ
    0.05
    æĹ¢
    0.05
    èĩªåĬ©
    0.05
    æ´»æĢ§çĤŃ
    0.05
     efficac
    0.05
    Activations Density 0.015%

    No Known Activations