© 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. 108219
    Prev
    Next
    INDEX
    Explanations

    Non-english, code, math

    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
     support
    -0.27
    渼
    -0.26
    hip
    -0.25
    ä¸įåĪ©
    -0.25
    pg
    -0.25
    cents
    -0.24
    Disallow
    -0.24
    ál
    -0.24
    (pg
    -0.24
    cura
    -0.23
    POSITIVE LOGITS
    éĵī
    0.27
     Woj
    0.27
     [{'
    0.26
    arias
    0.26
     [('
    0.26
    äºĨ大éĩıçļĦ
    0.26
    stein
    0.26
    specs
    0.25
    è¯ģæĺİ
    0.25
    åĩ¡æĺ¯
    0.25
    Activations Density 0.133%

    No Known Activations