© 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. 39927
    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
    languages
    -0.28
    plib
    -0.27
    -<?
    -0.26
     cuffs
    -0.26
    ('<?
    -0.26
    shed
    -0.25
    -years
    -0.24
    为ä¹ĭ
    -0.24
     '<?
    -0.24
    portlet
    -0.24
    POSITIVE LOGITS
     E
    0.34
    0.33
     S
    0.30
     The
    0.30
     H
    0.29
    桦
    0.29
     I
    0.29
     F
    0.28
     K
    0.28
     In
    0.28
    Activations Density 0.413%

    No Known Activations

    This feature has no known activations.