© 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. 7848
    Prev
    Next
    INDEX
    Explanations

    Prepositional/Auxiliary Phrases

    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
    ylene
    -0.27
    ìħ
    -0.26
     Thr
    -0.24
     conforme
    -0.24
     pellets
    -0.24
    çĶļ
    -0.24
    atables
    -0.24
    este
    -0.24
     latest
    -0.23
     Lounge
    -0.23
    POSITIVE LOGITS
    ensitive
    0.31
    æĸ¯åŁº
    0.27
    ä¸įåİ»
    0.26
    finity
    0.25
     insensitive
    0.24
    enko
    0.24
    :///
    0.24
     PROT
    0.24
    æĪĽ
    0.23
    寺éĻ¢
    0.23
    Activations Density 0.020%

    No Known Activations