© 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. 20809
    Prev
    Next
    INDEX
    Explanations

    NF-κB signaling pathway

    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
    æĴŀ
    -0.05
    صد
    -0.05
     poised
    -0.05
     (
    -0.05
    -0.05
    vedere
    -0.04
    :
    -0.04
     oper
    -0.04
    Mult
    -0.04
    odynamic
    -0.04
    POSITIVE LOGITS
    éĥ¨éŨèģĶåIJĪ
    0.07
    ériment
    0.07
    clair
    0.06
    æĸ°åĬłåĿ¡
    0.06
    teil
    0.06
    çĶµåĻ¨æľīéĻIJåħ¬åı¸
    0.06
    +')
    0.06
    anoi
    0.06
     Haush
    0.06
    èį§
    0.06
    Activations Density 0.156%

    No Known Activations