© 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. 40302
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     institutions
    -0.29
     institutes
    -0.28
     usu
    -0.26
     cubes
    -0.26
     institution
    -0.26
     memberships
    -0.25
     hypothesis
    -0.25
    vised
    -0.24
     experts
    -0.24
     seminars
    -0.24
    POSITIVE LOGITS
    ож
    0.29
    æĥ¯
    0.28
    оÑĦ
    0.27
    ин
    0.27
    路线
    0.27
    од
    0.27
    æĹłå£°
    0.27
    å½»åºķ
    0.26
    rus
    0.26
    çĹĽçĤ¹
    0.26
    Activations Density 57.349%

    No Known Activations

    This feature has no known activations.