© 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. 20-TRANSCODER-HP
    7. 107394
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å°±çŁ¥éģĵ
    -0.26
    åıijå±ķ模å¼ı
    -0.25
    åIJĬ
    -0.24
    URING
    -0.24
    partment
    -0.24
    sand
    -0.24
    èĥ½å¾ĹåĪ°
    -0.24
    //--
    -0.24
    ,:,:
    -0.23
    shall
    -0.23
    POSITIVE LOGITS
    (SP
    0.28
    ponsible
    0.28
    ix
    0.27
    çļĦåīįæıIJä¸ĭ
    0.25
    ãĥ¼ãĤ¹
    0.25
     Beh
    0.25
    abez
    0.25
    	SP
    0.25
     WITHOUT
    0.24
     behavioural
    0.24
    Activations Density 5.295%

    No Known Activations

    This feature has no known activations.