© 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. 161923
    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
    preneur
    -0.29
    çĦĻ
    -0.27
    è½®
    -0.26
    á»Ĭ
    -0.25
    á»ĭ
    -0.25
    年级
    -0.25
    urtle
    -0.25
     wheels
    -0.25
    blers
    -0.24
    VISIBLE
    -0.24
    POSITIVE LOGITS
    å¥
    0.28
    chio
    0.27
    oms
    0.27
    éĶij
    0.26
     pointer
    0.26
    eve
    0.25
    æĮĩ
    0.24
    _pointer
    0.24
    好人
    0.24
    åıijå±ķ空éĹ´
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.