© 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. 19155
    Prev
    Next
    INDEX
    Explanations

    the a

    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
     theirs
    -0.08
    .
    -0.06
    ↵
    -0.06
     ours
    -0.05
     ...
    -0.05
    ...
    -0.05
    inned
    -0.05
    å®Įæķ´
    -0.05
    æĸ°ä¸Ģ代
    -0.05
    好åIJ§
    -0.05
    POSITIVE LOGITS
    rije
    0.06
    èĬ±åľ¨
    0.06
    ÑĤÑĢеннÑıÑı
    0.06
    ordon
    0.05
     наÑģÑĤолÑĮко
    0.05
     COMPR
    0.05
     creden
    0.05
     McDon
    0.05
    ÑģÑĤÑĢой
    0.05
     gewähr
    0.05
    Activations Density 0.209%

    No Known Activations