© 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. 31-TRANSCODER-HP
    7. 18586
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æīĢ
    -0.97
    æīĢæīĢ
    -0.65
    åħ¶æīĢ
    -0.59
    æīĢæıIJä¾Ľ
    -0.58
    èĢĮ
    -0.53
    æīĢæīĢéķ¿
    -0.53
    æīĢæıIJä¾ĽçļĦ
    -0.52
    æīĢåģļçļĦ
    -0.52
    æīĢéľĢè¦ģ
    -0.49
    æīĢèĥ½
    -0.47
    POSITIVE LOGITS
    0.52
    ãģ®åł´åIJĪ
    0.26
    :def
    0.25
    åĩłçĤ¹
    0.25
     اÙĦØŃÙĤÙĬÙĤÙĬ
    0.24
     NaN
    0.24
    没è§ģè¿ĩ
    0.24
     undef
    0.23
    sic
    0.23
    _case
    0.23
    Activations Density 1.813%

    No Known Activations