© 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. 27-TRANSCODER-HP
    7. 57582
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     organ
    -0.27
    edException
    -0.26
    æľ¬èº«å°±æĺ¯
    -0.25
     himself
    -0.24
    çĶµè¯Ŀ
    -0.24
     uneven
    -0.24
     sur
    -0.24
    ä¸ĭ乡
    -0.24
     un
    -0.23
    åİ¿éķ¿
    -0.23
    POSITIVE LOGITS
     createState
    0.29
     ([[
    0.27
    icrosoft
    0.25
    etat
    0.25
     Tanks
    0.25
    åıĪæľī
    0.24
    ãĥĵãĥ«
    0.24
    ocz
    0.24
    asty
    0.23
    ickle
    0.23
    Activations Density 0.004%

    No Known Activations