© 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. 108576
    Prev
    Next
    INDEX
    Explanations

    names of things

    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
    su
    -0.32
    į°
    -0.31
    åħ¨æĿij
    -0.31
    sta
    -0.29
    meg
    -0.29
    owi
    -0.27
    stakes
    -0.27
    sf
    -0.27
    ี
    -0.27
    stab
    -0.26
    POSITIVE LOGITS
    eve
    0.28
    æݧèĤ¡
    0.28
    ele
    0.28
    er
    0.27
    tro
    0.27
    tty
    0.27
    ties
    0.26
    ev
    0.26
    ters
    0.26
    æī¯
    0.25
    Activations Density 2.420%

    No Known Activations