© 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. 17845
    Prev
    Next
    INDEX
    Explanations

    `.createFrom`

    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
    åľĪ
    -0.05
    Identification
    -0.05
     Identification
    -0.05
    ename
    -0.05
     Identified
    -0.05
    åı«
    -0.05
     bare
    -0.05
    Ident
    -0.05
     determined
    -0.05
    ja
    -0.05
    POSITIVE LOGITS
    agd
    0.07
    ÑĪек
    0.06
    urs
    0.06
    -et
    0.06
    ioned
    0.06
    èį¯æķĪ
    0.06
     ``(
    0.06
    regor
    0.06
    æĨ¬
    0.06
    .createFrom
    0.06
    Activations Density 0.003%

    No Known Activations