© 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. 17085
    Prev
    Next
    INDEX
    Explanations

    code syntax/file headers

    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
     cen
    -0.05
    man
    -0.05
    ee
    -0.05
    ism
    -0.05
    ı
    -0.05
    iseau
    -0.05
    éĢIJ
    -0.05
     fournisse
    -0.05
    c
    -0.05
    (NULL
    -0.05
    POSITIVE LOGITS
    dna
    0.06
    ongen
    0.06
    inos
    0.06
    à¹Ģà¸Ķ
    0.06
    è®°èĢħäºĨ解åĪ°
    0.06
    è¹Ī
    0.06
    νο
    0.06
    incon
    0.06
    onest
    0.06
    åı®
    0.06
    Activations Density 0.054%

    No Known Activations