© 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. 20-TRANSCODER-HP
    7. 130437
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪĨéħį
    -0.29
    (_,
    -0.28
     implic
    -0.27
     (_,
    -0.27
    ijľ
    -0.26
    auty
    -0.26
    çļĦåīįæıIJ
    -0.25
    felt
    -0.24
     surprises
    -0.24
    为空
    -0.24
    POSITIVE LOGITS
     tend
    0.31
     well
    0.28
     past
    0.28
     uncont
    0.27
     constitution
    0.27
    well
    0.26
    end
    0.26
    éĤ£åıª
    0.25
    ack
    0.25
     resting
    0.25
    Activations Density 0.047%

    No Known Activations

    This feature has no known activations.