© 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. 39699
    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
    éĹ®çŃĶ
    -0.31
    å¹´é¾Ħ
    -0.28
    å²ģ以ä¸Ĭ
    -0.28
    olas
    -0.28
    ascus
    -0.28
    reb
    -0.27
    å²ģ
    -0.27
    çĽ¸å¯¹
    -0.26
    è¿ĺ款
    -0.25
    art
    -0.25
    POSITIVE LOGITS
    åįıä¼ļä¼ļéķ¿
    0.26
     anyways
    0.25
     Nimbus
    0.24
    efault
    0.24
    boom
    0.24
    emens
    0.24
    STDOUT
    0.24
    å°ıå§IJ
    0.24
     vá»ijn
    0.23
    è¿ħçĮĽ
    0.23
    Activations Density 17.364%

    No Known Activations

    This feature has no known activations.