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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6009
    Prev
    Next
    INDEX
    Explanations

    Code/File data

    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
    SSIP
    -0.29
    çĪ¸çĪ¸å¦Īå¦Ī
    -0.29
    ppy
    -0.27
    å¤ļå¤ļ
    -0.26
    转移åĪ°
    -0.26
    quis
    -0.25
    lef
    -0.25
    è¿ĺæľīå¾Īå¤ļ
    -0.25
    åħ±è®¡
    -0.24
    ="//
    -0.24
    POSITIVE LOGITS
    ivitÃł
    0.27
     Relax
    0.26
    Tw
    0.26
     Lon
    0.26
     fundamentals
    0.26
    goo
    0.25
     infl
    0.25
    涨
    0.24
     Cla
    0.24
    åĨ³å¿ĥ
    0.24
    Activations Density 0.032%

    No Known Activations