© 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. 21796
    Prev
    Next
    INDEX
    Explanations

    until it fails to get 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
    è·µ
    -0.06
    ç³Ł
    -0.06
     Pomp
    -0.05
    åľ¨æł¡æľŁéĹ´
    -0.05
    preter
    -0.05
    ild
    -0.05
    å¤ĩ
    -0.05
    tro
    -0.05
     away
    -0.05
    tering
    -0.05
    POSITIVE LOGITS
     slugg
    0.07
    ä¸įåĨį
    0.06
     Stable
    0.06
    ä¸įåĨįæľī
    0.06
    last
    0.06
    ambang
    0.06
    åĨįä¹Ł
    0.06
     stagnant
    0.06
    LAST
    0.06
    ä¸įåĨįæĺ¯
    0.05
    Activations Density 0.027%

    No Known Activations