© 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. 17490
    Prev
    Next
    INDEX
    Explanations

    any questions or type

    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
    osotros
    -0.06
    usste
    -0.06
     avs
    -0.06
    aims
    -0.06
    spa
    -0.06
    žený
    -0.06
     simila
    -0.06
    Printf
    -0.06
     obiet
    -0.06
    åĩĿ
    -0.06
    POSITIVE LOGITS
    ely
    0.05
     bound
    0.05
    it
    0.05
    upply
    0.05
    éĻ¤
    0.05
    ite
    0.05
    .props
    0.05
    åħ¶ä¸º
    0.05
    ites
    0.05
    éĻ¤äºĨ
    0.05
    Activations Density 0.001%

    No Known Activations