© 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. 64517
    Prev
    Next
    INDEX
    Explanations

    News stories

    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
    Not in Any Lists

    No Comments

    Negative Logits
    çĩ®
    -0.28
     Mono
    -0.27
    导读
    -0.26
    öm
    -0.26
    éļıçĿĢ
    -0.26
    éĥ½å¾Ī
    -0.26
    rear
    -0.26
    apy
    -0.25
    alar
    -0.25
    äºĨä¸ĢäºĽ
    -0.25
    POSITIVE LOGITS
    ivism
    0.27
     scaling
    0.25
     AUX
    0.25
     intuitive
    0.25
    AtIndex
    0.25
     neutrality
    0.24
    manship
    0.24
    ees
    0.24
     Equivalent
    0.24
    -commit
    0.24
    Activations Density 0.918%

    No Known Activations