© 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. 25-TRANSCODER-HP
    7. 108827
    Prev
    Next
    INDEX
    Explanations

    way

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    对å¾ħ
    -0.27
     mist
    -0.27
    以为
    -0.26
     mis
    -0.26
    对ç«ĭ
    -0.26
    çģ°å°ĺ
    -0.26
    heels
    -0.25
    omal
    -0.25
     tired
    -0.25
     him
    -0.25
    POSITIVE LOGITS
    ä»»ä½ķ人
    0.30
    访
    0.28
    audi
    0.26
    principal
    0.26
     ways
    0.26
    ä»»ä½ķ
    0.25
     Daughter
    0.25
     granddaughter
    0.25
    äºĨä¸Ģæī¹
    0.24
    ä¸Ģèĩ´
    0.24
    Activations Density 0.154%

    No Known Activations