© 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. 19-TRANSCODER-HP
    7. 9532
    Prev
    Next
    INDEX
    Explanations

    Grape

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¯ĨåĪĩ
    -0.31
    çĶį
    -0.26
    mapper
    -0.25
     suggest
    -0.24
    åĤ¬
    -0.24
    @Api
    -0.24
    åºĬä½į
    -0.23
     Catalyst
    -0.23
    (mapping
    -0.23
     catalyst
    -0.22
    POSITIVE LOGITS
    acula
    0.27
    ç§ĭ
    0.26
    uess
    0.25
    iability
    0.24
    abs
    0.24
    faction
    0.24
    iable
    0.24
     localization
    0.24
    该项
    0.23
    à¸ģรรม
    0.23
    Activations Density 0.007%

    No Known Activations