© 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. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 39746
    Prev
    Next
    INDEX
    Explanations

    random facts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ģ个æĸ°çļĦ
    -0.28
    ounder
    -0.26
    è¿Ļ
    -0.26
    orc
    -0.26
    个人è§ĤçĤ¹
    -0.25
    ç»°
    -0.25
    è¿ŀ线
    -0.25
    è¯ķè¡Į
    -0.24
    èĤ¡å¸Ĥ
    -0.24
    åĽ½åĨħ
    -0.24
    POSITIVE LOGITS
    ue
    0.29
    çļĦéĩįè¦ģæĢ§
    0.28
     Kob
    0.25
    ERO
    0.25
     önem
    0.24
    Ð¡ÐŁ
    0.24
    KP
    0.24
     pressure
    0.24
     prevented
    0.24
    åľ°
    0.23
    Activations Density 0.063%

    No Known Activations