© 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. 18780
    Prev
    Next
    INDEX
    Explanations

    different kinds or types

    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
    à¹Ħหรà¹Ī
    -0.08
    ï¸İ
    -0.07
     beiden
    -0.07
    acter
    -0.07
    ï¸ı
    -0.07
    abis
    -0.07
    oplast
    -0.07
    oÄį
    -0.07
     zaak
    -0.07
     recus
    -0.07
    POSITIVE LOGITS
    ness
    0.06
    ities
    0.06
    s
    0.05
    éĩijçİī
    0.05
    ipher
    0.05
     e
    0.05
     protagonistas
    0.05
    ies
    0.04
    ification
    0.04
    ori
    0.04
    Activations Density 0.008%

    No Known Activations