© 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. 21971
    Prev
    Next
    INDEX
    Explanations

    pre-built, predefined, pre-made, preset

    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
    è¿Ŀ
    -0.06
    åİŁæĿ¥çļĦ
    -0.06
    ç´łè´¨
    -0.05
    wik
    -0.05
     already
    -0.05
    èĩªæľī
    -0.05
    æī¶
    -0.05
    ä¹IJ
    -0.05
     pre
    -0.05
    å·²æľīçļĦ
    -0.05
    POSITIVE LOGITS
    åĪ©å®³
    0.06
    geist
    0.06
     gav
    0.06
    dert
    0.06
    ight
    0.06
    åıĹå½±åĵį
    0.05
    gab
    0.05
    ç´IJ
    0.05
    IBC
    0.05
    è¦ģæıIJé«ĺ
    0.05
    Activations Density 0.014%

    No Known Activations