© 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. 17401
    Prev
    Next
    INDEX
    Explanations

    compound chemical names

    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
    óf
    -0.06
     tÃłn
    -0.06
    (er
    -0.06
    abis
    -0.05
    onic
    -0.05
    ickle
    -0.05
    Ñĥж
    -0.05
    常å§Ķä¼ļ
    -0.05
     verticale
    -0.05
    ouch
    -0.05
    POSITIVE LOGITS
     подÑģ
    0.07
    æĬĬ头
    0.06
    ible
    0.06
    åħĥé¦ĸ
    0.06
    ç§ģ
    0.05
    æıIJ
    0.05
    åĽļ
    0.05
    çĪ·
    0.05
    ç©ºåľ°
    0.05
    wner
    0.05
    Activations Density 0.010%

    No Known Activations