© 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. 17693
    Prev
    Next
    INDEX
    Explanations

    hope this helps

    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
     solicit
    -0.06
    oct
    -0.05
     bando
    -0.05
    erver
    -0.05
    å®Ī
    -0.05
    çݯå¢ĥä¼ĺç¾İ
    -0.05
     Remain
    -0.05
    .servlet
    -0.05
    åĪ°äºĨ
    -0.05
    ander
    -0.05
    POSITIVE LOGITS
    arie
    0.08
    duct
    0.08
    forth
    0.07
    ำ
    0.07
    iah
    0.06
    джÑĥ
    0.06
    aight
    0.06
     perspectiv
    0.06
    ducted
    0.06
    asse
    0.06
    Activations Density 0.016%

    No Known Activations