© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 9003
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    éĢīåĩº
    -0.29
     Trit
    -0.27
    ë©°
    -0.27
    çĿĢ
    -0.25
    éĢī
    -0.25
    unda
    -0.25
    èµ°
    -0.24
    åľ°
    -0.24
    ground
    -0.24
    åı£
    -0.24
    POSITIVE LOGITS
    /activity
    0.26
    eenth
    0.26
     lawy
    0.26
    rif
    0.25
    fsp
    0.25
    /array
    0.24
    çĴĭ
    0.23
    isson
    0.23
     blogging
    0.23
    å¿ħçĦ¶ä¼ļ
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.