© 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. 107948
    Prev
    Next
    INDEX
    Explanations

    / and ,

    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
    ön
    -0.27
    ä½ľèĢħæľ¬äºº
    -0.26
     prefect
    -0.25
    èijŃ
    -0.25
    xDB
    -0.24
    .chapter
    -0.24
    sonian
    -0.24
    åĮĸ
    -0.23
    imdi
    -0.23
    itect
    -0.23
    POSITIVE LOGITS
    ä»Ĭå¹´
    0.62
    åݻ年
    0.49
    åħ¬åħĥ
    0.48
    ä¸Ĭä¸ĸ纪
    0.42
    åħ¬åħĥåīį
    0.40
     year
    0.40
     nÄĥm
    0.40
    åľ¨ä»Ĭå¹´
    0.39
    (year
    0.36
     tahun
    0.36
    Activations Density 4.091%

    No Known Activations