© 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. 8888
    Prev
    Next
    INDEX
    Explanations

    award

    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
    æĬ½æŁ¥
    -0.26
     retard
    -0.25
     darken
    -0.25
    adians
    -0.24
    ateur
    -0.24
     contact
    -0.24
     damned
    -0.24
    çĭĻåĩ»
    -0.24
    аÑĤелÑĮ
    -0.23
    æŁ¥å°ģ
    -0.23
    POSITIVE LOGITS
    ç²ĺ
    0.29
     Recover
    0.25
    端
    0.25
    èļģ
    0.25
    ä¸īçĤ¹
    0.25
     aio
    0.24
    èĬ±çĵ£
    0.24
    inherit
    0.24
    èĤ©èĨĢ
    0.24
    æĹħéĢĶ
    0.24
    Activations Density 0.034%

    No Known Activations