© 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. 18491
    Prev
    Next
    INDEX
    Explanations

    labels and aliases

    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
    çĪ±ä¸į
    -0.06
    tag
    -0.06
     punc
    -0.06
     kans
    -0.05
    ìĦ¸ë¥¼
    -0.05
    決åĭĿ
    -0.05
     tightly
    -0.05
    å®ŀéĻħæݧåĪ¶æĿĥ
    -0.05
     gang
    -0.05
     ÙĦاÙħ
    -0.05
    POSITIVE LOGITS
    gend
    0.05
    å®ĮæĪIJçļĦ
    0.05
     convainc
    0.05
    orp
    0.05
    rique
    0.05
    lated
    0.05
    inou
    0.05
    leter
    0.05
    åľ°å®ĮæĪIJ
    0.05
    atus
    0.05
    Activations Density 0.001%

    No Known Activations