© 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. 17209
    Prev
    Next
    INDEX
    Explanations

    spirit of

    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
    orsch
    -0.08
    ÏĤ
    -0.07
    avers
    -0.07
    OrUpdate
    -0.07
    ãģ¦
    -0.06
    yers
    -0.06
    øy
    -0.06
    jenigen
    -0.06
    oley
    -0.06
    exual
    -0.06
    POSITIVE LOGITS
    amente
    0.06
    urally
    0.05
     дÑĥÑħ
    0.05
    ike
    0.05
    å±Ī
    0.05
    ÑģÑĤавлÑıеÑĤÑģÑı
    0.05
     sake
    0.05
    halt
    0.05
     espÃŃrito
    0.05
    iox
    0.05
    Activations Density 0.005%

    No Known Activations