© 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. 39868
    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
    髹
    -0.29
    byn
    -0.28
    ymoon
    -0.27
     adj
    -0.27
     cob
    -0.26
     ([[
    -0.25
    asthan
    -0.25
    ï½ŀ↵↵
    -0.25
    udeau
    -0.24
    ldre
    -0.24
    POSITIVE LOGITS
    åĨ²
    0.29
    åı°ä¸Ĭ
    0.29
    åĬ²
    0.29
     needless
    0.28
    马
    0.27
    件
    0.27
    夹
    0.26
    åıĪä¸Ģ次
    0.26
    MR
    0.26
    ä¼Ĺ
    0.26
    Activations Density 10.292%

    No Known Activations

    This feature has no known activations.