© 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. 19906
    Prev
    Next
    INDEX
    Explanations

    buyers and clients

    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
    lej
    -0.07
    opr
    -0.07
    ç»ıèIJ¥çĬ¶æĢģ
    -0.06
    amel
    -0.06
    zd
    -0.06
    Submitted
    -0.06
    agements
    -0.06
     ê³Ħ
    -0.06
    isos
    -0.06
    åħ¥éĻ¢
    -0.06
    POSITIVE LOGITS
    -minded
    0.06
    unia
    0.05
    Âł
    0.05
    çļĦåĨ³å®ļ
    0.05
    èĥ½æ»¡è¶³
    0.05
    亥
    0.05
     strony
    0.05
    端åºĦ
    0.05
     clubs
    0.05
    Criteria
    0.05
    Activations Density 0.030%

    No Known Activations