© 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. 163798
    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
    (":/
    -0.26
    ลาย
    -0.25
     Hv
    -0.24
    ç´Ĭä¹±
    -0.24
    æ½¼
    -0.24
    WAY
    -0.24
    éĶĢæ¯ģ
    -0.24
     lay
    -0.23
    urre
    -0.23
    adena
    -0.23
    POSITIVE LOGITS
    bond
    0.27
    ilig
    0.26
    wright
    0.25
    straint
    0.25
     âĪ§
    0.25
    PG
    0.23
     powered
    0.23
    logan
    0.23
     bond
    0.23
     newcom
    0.23
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.