© 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
    2. Qwen3-4B
    3. 25-TRANSCODER-HP
    4. 107720
    Prev
    Next
    INDEX
    Explanations

    6

    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
     Dia
    -0.29
     blat
    -0.29
    hana
    -0.28
    çıī
    -0.26
     Diameter
    -0.26
    人寿
    -0.26
     brazil
    -0.26
    aina
    -0.25
    olie
    -0.24
    çIJª
    -0.24
    POSITIVE LOGITS
    6
    0.47
     Sixth
    0.41
     sixth
    0.40
    åħŃ
    0.38
    第åħŃ
    0.38
    åħŃå¹´
    0.37
     six
    0.37
    åħŃ大
    0.35
    Six
    0.34
     اÙĦسادس
    0.33
    Activations Density 1.012%

    No Known Activations