© 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. 162521
    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
    驳
    -0.29
    izedName
    -0.28
    æµ·è¿IJ
    -0.27
    ledon
    -0.27
    å®ŀå¹²
    -0.25
    .har
    -0.25
    OCR
    -0.25
    æīįèĥ½å¤Ł
    -0.24
    -decoration
    -0.24
    å¿ĥå¾Ĺ
    -0.24
    POSITIVE LOGITS
     mount
    0.27
     straw
    0.25
    å±±ä¸Ĭ
    0.25
    äºĮ代
    0.24
     v
    0.24
    ìn
    0.24
    inc
    0.24
    ç¥ŀ
    0.23
     readline
    0.23
    ":"","
    0.23
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.