© 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. 163188
    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
    çļĦçľ¼
    -0.29
     gan
    -0.28
    iddy
    -0.28
    iro
    -0.27
     rat
    -0.26
    iez
    -0.24
     Roth
    -0.24
     handleMessage
    -0.24
    AAC
    -0.24
    BAT
    -0.24
    POSITIVE LOGITS
    _weak
    0.30
    Weak
    0.28
    æĭ³
    0.26
    .amazonaws
    0.26
     Weak
    0.26
    çĩĶ
    0.25
     weak
    0.24
    Storm
    0.24
    quist
    0.24
     Preconditions
    0.24
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.