© 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. 20-TRANSCODER-HP
    7. 140795
    Prev
    Next
    INDEX
    Explanations

    Software/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     segment
    -0.31
    ä½ķå¤Ħ
    -0.30
     corridors
    -0.30
     Segment
    -0.30
     segments
    -0.29
    UDO
    -0.28
    ä¸Ģè§Ĵ
    -0.28
    segment
    -0.28
     specific
    -0.27
    -specific
    -0.27
    POSITIVE LOGITS
    åĢ«
    0.27
    opsis
    0.27
    äºĨä¸Ģéģį
    0.26
    볬
    0.25
    æķĽ
    0.25
     mies
    0.24
    +.
    0.24
    çļĦæķĪæŀľ
    0.24
    åĻ«
    0.24
    -transform
    0.23
    Activations Density 33.511%

    No Known Activations