© 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. 39698
    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
    -0.47
     L
    -0.41
     D
    -0.41
     My
    -0.39
     Quick
    -0.39
     E
    -0.38
     Me
    -0.38
     S
    -0.38
     Any
    -0.38
     Re
    -0.38
    POSITIVE LOGITS
     ÐIJлекÑģан
    0.43
    пÑĢоÑĦеÑģÑģионал
    0.39
    -------------</
    0.39
     ÐĶм
    0.38
    медиÑĨинÑģк
    0.38
    íĹĢ
    0.37
     Câm
    0.37
     ÐĶмиÑĤÑĢ
    0.36
    GuidId
    0.34
     поÑģколÑĮ
    0.34
    Activations Density 0.456%

    No Known Activations

    This feature has no known activations.