© 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. 18269
    Prev
    Next
    INDEX
    Explanations

    reported speech

    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
    atoires
    -0.06
    RAY
    -0.06
     اÙĦتد
    -0.06
    å®ŀåĨµ
    -0.05
    gur
    -0.05
    大åĪĢ
    -0.05
    Ñĥбли
    -0.05
    égor
    -0.05
    beit
    -0.05
    UCT
    -0.05
    POSITIVE LOGITS
    eken
    0.06
    born
    0.05
    hold
    0.05
     sequence
    0.05
     Pres
    0.05
    err
    0.05
     contingent
    0.05
    estone
    0.05
    oner
    0.05
    yc
    0.05
    Activations Density 0.091%

    No Known Activations