© 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. 108572
    Prev
    Next
    INDEX
    Explanations

    non

    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
     neither
    -0.27
    ä¸įåIJĪ
    -0.27
     Initialise
    -0.26
    drv
    -0.26
     lik
    -0.26
     ConfigurationManager
    -0.25
     chains
    -0.24
    brains
    -0.24
     senses
    -0.24
    attrs
    -0.24
    POSITIVE LOGITS
     slept
    0.29
    -tr
    0.28
    -print
    0.27
    çī¹
    0.27
    -design
    0.27
    ovel
    0.26
    åĤ¬
    0.26
    etheless
    0.26
    -divider
    0.26
    heit
    0.26
    Activations Density 1.251%

    No Known Activations