© 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. 142574
    Prev
    Next
    INDEX
    Explanations

    3

    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
    ableObject
    -0.31
    redd
    -0.28
    -Clause
    -0.26
    çł°
    -0.26
    å·²ä¹ħ
    -0.26
    ected
    -0.25
     cooperating
    -0.25
    ariat
    -0.25
    ArrayOf
    -0.25
    olis
    -0.24
    POSITIVE LOGITS
     kap
    0.27
     ghetto
    0.25
    èģĶç³»
    0.25
     fel
    0.25
    _mut
    0.24
    _usage
    0.24
    ãģİ
    0.24
    вали
    0.24
    onnement
    0.24
     каÑĢÑĤ
    0.23
    Activations Density 8.507%

    No Known Activations