© 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. 18455
    Prev
    Next
    INDEX
    Explanations

    many of

    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
    junk
    -0.06
     happening
    -0.06
    abili
    -0.06
    isah
    -0.06
    iett
    -0.06
    noc
    -0.05
    åħ¶ä¸ŃçļĦ
    -0.05
    æŃ»ä¸į
    -0.05
     receta
    -0.05
    .HttpStatus
    -0.05
    POSITIVE LOGITS
     afar
    0.06
    æĮĩ导åĴĮ
    0.05
    ant
    0.05
    æĸ½è¡Į
    0.05
    äºĨä¸ĢåĪĩ
    0.05
    å®ŀæĸ½
    0.05
    æĺ¯ä¸ĢåĪĩ
    0.05
    idata
    0.05
    ifes
    0.05
     stip
    0.05
    Activations Density 0.007%

    No Known Activations