© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18576
    Prev
    Next
    INDEX
    Explanations

    human rights and the unborn

    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
    atoire
    -0.06
    è®°è½½
    -0.05
    दा
    -0.05
     unbiased
    -0.05
     Lois
    -0.05
    برد
    -0.05
     ç§ģ
    -0.05
    Fre
    -0.05
    Ùģس
    -0.05
    æıIJçĤ¼
    -0.05
    POSITIVE LOGITS
    ç±į
    0.06
    пелÑĮ
    0.06
    ÑĪеÑĢ
    0.06
    iq
    0.06
     huk
    0.06
    åĽłä¸ºå®ĥ们
    0.06
    èĦĨå¼±
    0.06
    æĬĬ她
    0.06
    ÙĤاط
    0.06
     preempt
    0.06
    Activations Density 0.010%

    No Known Activations