© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 23398
    Prev
    Next
    INDEX
    Explanations

    personal opinions, feelings

    np_max-act · gemini-2.0-flash
    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
    Negative Logits
    åīįéĢĶ
    -0.27
    åĢº
    -0.27
    åīįæĻ¯
    -0.27
    ä¹ĭ举
    -0.26
    wer
    -0.26
    第ä¸Ģ家
    -0.26
     Edinburgh
    -0.26
    ä¸Ģ年级
    -0.24
    åľ¨è¿ĻéĩĮ
    -0.24
     Cand
    -0.24
    POSITIVE LOGITS
    åĸľæ¬¢
    0.40
     prefers
    0.35
    ä¹łæĥ¯
    0.35
     preferring
    0.34
     gerne
    0.33
     prefer
    0.32
    preferred
    0.32
     preference
    0.31
    prefer
    0.31
    _preference
    0.31
    Activations Density 0.017%

    No Known Activations