© 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. 18311
    Prev
    Next
    INDEX
    Explanations

    risk assessment

    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
     Zoo
    -0.05
    imes
    -0.05
    olith
    -0.05
     cass
    -0.05
    仪
    -0.05
     Parm
    -0.05
     brand
    -0.05
     inst
    -0.05
    ITES
    -0.05
     fest
    -0.05
    POSITIVE LOGITS
    æķ¬çķı
    0.07
    æķı
    0.06
     Risk
    0.06
     Inh
    0.06
     conditioned
    0.06
    æĥ§
    0.06
    éĺ²æݧ
    0.06
    nature
    0.06
    ừng
    0.06
    åĪ©çī©
    0.06
    Activations Density 0.008%

    No Known Activations