© 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. 108910
    Prev
    Next
    INDEX
    Explanations

    Pop

    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
     rigor
    -0.26
    èĥ¼
    -0.25
    worthy
    -0.25
    èĩªåįij
    -0.25
    ByExample
    -0.25
    /fa
    -0.24
    èIJĬ
    -0.24
     unins
    -0.24
    umas
    -0.24
     forgiving
    -0.24
    POSITIVE LOGITS
    å¼¹
    0.35
    corn
    0.35
    .Pop
    0.32
     Pop
    0.31
    ulist
    0.30
    edom
    0.29
    (pop
    0.28
    ularity
    0.27
     pop
    0.27
    udd
    0.27
    Activations Density 0.992%

    No Known Activations