© 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. 23-TRANSCODER-HP
    7. 24660
    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
    idents
    -0.27
    çĸļ
    -0.26
    é¢ļ
    -0.26
     HEL
    -0.26
    okit
    -0.25
    ä¹Łå¥½
    -0.25
    -gay
    -0.24
    äºĨåĩł
    -0.24
    èIJ¥åķĨ
    -0.24
     Bucc
    -0.24
    POSITIVE LOGITS
    åħ·ä½ĵçļĦ
    0.31
    åħ·ä½ĵ
    0.27
    çļĦåħ·ä½ĵ
    0.26
    第äºĮç§į
    0.26
    æľºåħ³
    0.26
    lesia
    0.26
    me
    0.25
     dirt
    0.25
    egral
    0.25
    ossa
    0.25
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.