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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163117
    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
    çĤ¹è¯Ħ
    -0.28
     base
    -0.27
    Base
    -0.25
    base
    -0.25
    ots
    -0.25
    entin
    -0.25
    ä¸Ģ带
    -0.25
     opt
    -0.24
    vez
    -0.23
     goal
    -0.23
    POSITIVE LOGITS
     fict
    0.29
    acles
    0.26
     fiction
    0.25
    èĻļæŀĦ
    0.25
    èĦĤ
    0.25
    麽
    0.24
    oyer
    0.23
     Hum
    0.23
     hum
    0.23
     Hü
    0.23
    Activations Density 0.029%

    No Known Activations

    This feature has no known activations.