© 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. 6720
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    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
    å°ıåĦ¿
    -0.26
     n
    -0.25
    orical
    -0.24
    UTE
    -0.24
    dhcp
    -0.23
    NYSE
    -0.23
    iffies
    -0.23
    åĥ®
    -0.23
     conv
    -0.23
    styl
    -0.23
    POSITIVE LOGITS
    otte
    0.26
    permalink
    0.26
     promot
    0.26
    otos
    0.25
    bia
    0.24
    åĽŀåĪ°
    0.24
     neighbor
    0.24
    [".
    0.24
    BOTTOM
    0.24
    ׼×ķת
    0.23
    Activations Density 0.142%

    No Known Activations