© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17142
    Prev
    Next
    INDEX
    Explanations

    seemingly or apparently

    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
    æŃ¥
    -0.06
     N
    -0.05
    (s
    -0.05
    -m
    -0.05
    b
    -0.05
    ken
    -0.05
    eval
    -0.05
    d
    -0.05
    bi
    -0.05
     even
    -0.05
    POSITIVE LOGITS
     vél
    0.07
     ador
    0.06
    trie
    0.06
     **—
    0.06
    ç®Ģ
    0.06
     Parkplätze
    0.06
    ponsors
    0.06
    voirs
    0.06
    jubl
    0.06
    criv
    0.06
    Activations Density 0.002%

    No Known Activations