© 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. 161791
    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
    ãģ¤ãĤĤãĤĬ
    -0.28
    Raised
    -0.28
     intents
    -0.26
     raised
    -0.26
     variables
    -0.26
     raising
    -0.26
     اÙĦعÙĦÙĬا
    -0.26
     intent
    -0.26
     concluded
    -0.25
     supers
    -0.25
    POSITIVE LOGITS
    èĬĹ
    0.33
    èĥĨ
    0.28
    akis
    0.28
    骨æŀ¶
    0.26
    ambi
    0.26
    edy
    0.26
    çIJIJ
    0.25
    è¿ĺæľīå¾Īå¤ļ
    0.25
    ush
    0.24
    phere
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.