© 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. 57901
    Prev
    Next
    INDEX
    Explanations

    events that cause surprise

    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
    è§Ħå¾ĭ
    -0.30
    {|
    -0.26
    itura
    -0.25
     Ferguson
    -0.25
    irates
    -0.24
    该åħ¬åı¸
    -0.24
     inverted
    -0.24
     True
    -0.24
    ception
    -0.23
    Human
    -0.23
    POSITIVE LOGITS
    çłĶ究人åijĺ
    0.31
    çĶļèĩ³
    0.29
     researchers
    0.29
    çĶļèĩ³æĺ¯
    0.27
    æľīä¸Ģ天
    0.26
     mouths
    0.26
     mobility
    0.26
     Laud
    0.25
    å®
    0.25
     imp
    0.25
    Activations Density 0.004%

    No Known Activations