© 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. 108472
    Prev
    Next
    INDEX
    Explanations

    Bud

    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
     Pyramid
    -0.27
    o
    -0.27
    oor
    -0.26
    e
    -0.26
    sequences
    -0.25
    ustralia
    -0.24
    å°ijäºĨ
    -0.24
    eve
    -0.24
    OrNil
    -0.24
    ipl
    -0.23
    POSITIVE LOGITS
     weld
    0.29
     spat
    0.28
     resistant
    0.28
     wre
    0.27
    ÑĩаÑĤ
    0.26
     begging
    0.25
     fle
    0.25
     autof
    0.24
    -eff
    0.24
    èĢĮæĪIJ
    0.24
    Activations Density 0.373%

    No Known Activations