© 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. 17361
    Prev
    Next
    INDEX
    Explanations

    legal or policy statements

    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
     certain
    -0.06
     опÑĢеделÑij
    -0.05
    æĬĹçĸ«
    -0.05
     essentially
    -0.05
     relat
    -0.05
    æķ´ä¸ªéĹ®é¢ĺ
    -0.05
    agues
    -0.05
     hypothetical
    -0.05
     basically
    -0.05
     Trad
    -0.05
    POSITIVE LOGITS
    åīį款
    0.07
    æĪijä¹Łåİ»
    0.06
    è´Łè´£åĪ¶
    0.06
    asion
    0.06
     melip
    0.06
    åįķ项éĢīæĭ©é¢ĺ
    0.06
    å¿ħç»ı
    0.06
    请éĢīæĭ©
    0.06
    meno
    0.06
    æ
    0.06
    Activations Density 0.013%

    No Known Activations