© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162689
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çľĭä»ĸ
    -0.27
     Mini
    -0.27
    lettes
    -0.26
    让ä»ĸ
    -0.26
    让她
    -0.26
     заÑĤ
    -0.26
    éĹ®ä»ĸ
    -0.25
    pbs
    -0.25
    便
    -0.24
     Red
    -0.24
    POSITIVE LOGITS
    å¡ŀ
    0.28
    ến
    0.26
    ients
    0.25
    ;base
    0.25
    bsite
    0.24
    åħħåĪĨ
    0.24
    entities
    0.24
    seq
    0.24
     Foley
    0.24
    é«ĺ端
    0.24
    Activations Density 0.036%

    No Known Activations

    This feature has no known activations.