© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7363
    Prev
    Next
    INDEX
    Explanations

    Numbers and coding

    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
    Not in Any Lists

    No Comments

    Negative Logits
     cra
    -0.32
    fmt
    -0.29
    leh
    -0.26
    æ§ĺ
    -0.26
    è§Ĩè§ī
    -0.25
    пÑĥÑĤ
    -0.25
    éļIJå½¢
    -0.25
    形象
    -0.25
     Benson
    -0.25
    ________________________________
    -0.25
    POSITIVE LOGITS
     Dep
    0.25
    gran
    0.24
     dep
    0.24
     FileManager
    0.24
    rollers
    0.24
    probe
    0.24
    èĥ½æī¾åĪ°
    0.24
    é¢Ŀ头
    0.23
    abilia
    0.23
    rac
    0.23
    Activations Density 0.018%

    No Known Activations