© 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. 20999
    Prev
    Next
    INDEX
    Explanations

    time durations

    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
    anken
    -0.06
    rts
    -0.06
    afil
    -0.06
    andar
    -0.06
    addon
    -0.06
    foro
    -0.06
    æIJģ
    -0.06
     slowdown
    -0.06
    æ¦Ĩ
    -0.06
    ramento
    -0.06
    POSITIVE LOGITS
    éľĢè¦ģåıĬæŶ
    0.05
    å¾Ĺå¿«
    0.05
     sve
    0.05
     solar
    0.05
    çĶ¨è¿ĩ
    0.05
     coron
    0.05
    åıĬæŶ
    0.05
    使çĶ¨è¯¥
    0.05
    controlled
    0.04
    å¾Īå¿«å°±ä¼ļ
    0.04
    Activations Density 0.041%

    No Known Activations