© 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. 20751
    Prev
    Next
    INDEX
    Explanations

    requires, needs, involves

    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
    æĮijæĪĺåĴĮ
    -0.07
    éļ¾åº¦å¤§
    -0.06
    ishly
    -0.06
    åĽłåľ°
    -0.06
    гÑĢÑĥ
    -0.06
    å¿ħ究
    -0.06
    åıĬè¦ģæ±Ĥ
    -0.06
    åĽłæ¶īå«Į
    -0.06
    angep
    -0.06
    æĸ¹æ³ķåıĬ
    -0.06
    POSITIVE LOGITS
    æ¯į
    0.05
    ä¸ļ
    0.05
    rene
    0.05
    trim
    0.05
    alom
    0.05
    urbation
    0.05
    æĢģ
    0.05
    roso
    0.05
    ahui
    0.05
    iego
    0.05
    Activations Density 0.002%

    No Known Activations