© 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. 8531
    Prev
    Next
    INDEX
    Explanations

    As

    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
    鹫
    -0.27
    ãģĤãĤĬ
    -0.27
    iesta
    -0.27
    CSI
    -0.26
    ÅŁ
    -0.26
    æłĩé¢ĺ
    -0.26
    iest
    -0.25
     Departments
    -0.25
    æĻºæħ§åŁİå¸Ĥ
    -0.24
    oy
    -0.24
    POSITIVE LOGITS
    çŀĴ
    0.26
    å·´å·´
    0.25
     diagram
    0.25
    ampa
    0.25
    atform
    0.25
     didn
    0.25
     gave
    0.25
    eteor
    0.25
    cket
    0.24
    åĨ³å®ļäºĨ
    0.24
    Activations Density 0.149%

    No Known Activations