© 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. 108912
    Prev
    Next
    INDEX
    Explanations

    information and data

    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
    ä¸įçķĻ
    -0.31
    æľĢåIJĪéĢĤ
    -0.25
     strongest
    -0.25
    culo
    -0.25
    (Adapter
    -0.25
    &B
    -0.24
    'aff
    -0.24
     überhaupt
    -0.24
    éĵ
    -0.24
    ä¾
    -0.24
    POSITIVE LOGITS
     related
    0.30
    anny
    0.30
     regarding
    0.30
    缸åħ³ä¿¡æģ¯
    0.28
    éĤ£åıª
    0.28
    缸åħ³
    0.27
     tokens
    0.26
    缸åħ³çļĦ
    0.26
     shortcuts
    0.26
     pertinent
    0.25
    Activations Density 0.913%

    No Known Activations