© 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. 9474
    Prev
    Next
    INDEX
    Explanations

    vent

    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
    IBE
    -0.25
     retention
    -0.24
     Ung
    -0.24
    ëĦĮ
    -0.24
    ennen
    -0.24
    çĥĪ
    -0.23
    ibi
    -0.23
    yw
    -0.23
    este
    -0.23
    iram
    -0.23
    POSITIVE LOGITS
    使ä¹ĭ
    0.35
    让å®ĥ
    0.26
    опÑĢедел
    0.25
     Affero
    0.25
    使åħ¶
    0.25
    -ish
    0.23
    ä¸ĢæŶ
    0.23
    grown
    0.23
    Defense
    0.23
    ä¸Ģåıªæīĭ
    0.23
    Activations Density 0.017%

    No Known Activations