© 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. 108132
    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
    绿èī²éĢļéģĵ
    -0.31
    åħ¬å¸ĥçļĦ
    -0.29
    æµģåĩº
    -0.27
    ä¸Ģ份
    -0.26
    estroy
    -0.26
    ä¸Ģäºĭ
    -0.25
    -public
    -0.25
     nature
    -0.25
    èĩªåªĴä½ĵ
    -0.24
     Nature
    -0.24
    POSITIVE LOGITS
     perfectly
    0.25
     últ
    0.25
    ascar
    0.24
     controversial
    0.23
    CED
    0.23
    ASC
    0.23
    çĽĪ
    0.23
    å®Į
    0.22
    #.
    0.22
     Invocation
    0.22
    Activations Density 13.533%

    No Known Activations

    This feature has no known activations.