© 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. 18108
    Prev
    Next
    INDEX
    Explanations

    possibility, allowance, or conceivability

    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
    rof
    -0.06
    rint
    -0.06
    æķ°åįĥ
    -0.06
    å¾ĹåĬĽ
    -0.05
     hạng
    -0.05
    ganggu
    -0.05
    ä¸Ģå®ļç¨ĭ度
    -0.05
    umos
    -0.05
    è®®
    -0.05
    Performed
    -0.05
    POSITIVE LOGITS
     possibility
    0.07
     allowed
    0.07
     possible
    0.07
     possibilité
    0.07
    çļĦåı¯èĥ½æĢ§
    0.07
    åħģ许
    0.07
     imaginable
    0.07
     conceivable
    0.07
    allow
    0.06
     permitted
    0.06
    Activations Density 0.095%

    No Known Activations