© 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. 22-TRANSCODER-HP
    7. 86923
    Prev
    Next
    INDEX
    Explanations

    Conversational fillers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    订
    -0.28
    ****↵
    -0.25
    جر
    -0.23
    åĬłåħ¥äºĨ
    -0.23
     PD
    -0.23
    æŀ¢
    -0.23
     v
    -0.23
     —↵↵
    -0.22
    ».
    -0.22
    aint
    -0.22
    POSITIVE LOGITS
    however
    0.31
     however
    0.27
    beck
    0.26
    etheless
    0.26
     représ
    0.25
     lastIndex
    0.25
    _First
    0.24
     seeming
    0.24
    However
    0.23
    PerPixel
    0.23
    Activations Density 0.045%

    No Known Activations