© 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. 7438
    Prev
    Next
    INDEX
    Explanations

    together

    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
     perfection
    -0.26
    objectId
    -0.25
    éĵİ
    -0.25
    åĪ³
    -0.25
     concepts
    -0.24
    ins
    -0.24
     objectId
    -0.24
    ="../../
    -0.24
    èĮħ
    -0.23
    _METHOD
    -0.23
    POSITIVE LOGITS
    acket
    0.30
    fuck
    0.27
    ling
    0.25
    .nih
    0.25
    eselect
    0.25
    athe
    0.25
     politic
    0.24
     Ryder
    0.24
     incidental
    0.24
     íĶ¼íķ´
    0.24
    Activations Density 0.026%

    No Known Activations