© 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. 19034
    Prev
    Next
    INDEX
    Explanations

    foundational or critical information

    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
    æĪĸ以ä¸Ĭ
    -0.06
    å°Ķ
    -0.06
    ä»Ģä¹ĪæĥħåĨµ
    -0.05
    emsp
    -0.05
    à¹ģà¸ļà¸ļà¸Ļีà¹ī
    -0.05
    romatic
    -0.05
     standoff
    -0.05
    les
    -0.05
    asionally
    -0.05
    ä¸ĢæŶ
    -0.05
    POSITIVE LOGITS
    áĥ§áĥĿ
    0.06
    ovu
    0.06
    adeira
    0.06
    onta
    0.06
    æ®Ĭä¸įçŁ¥
    0.05
    atera
    0.05
    è·¯åĮĹ
    0.05
    endu
    0.05
     Ninh
    0.05
    ivi
    0.05
    Activations Density 0.007%

    No Known Activations