© 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. 108857
    Prev
    Next
    INDEX
    Explanations

    stress

    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
    è§ĦåĪĴ建设
    -0.31
     Ordering
    -0.28
    ä¸ĭ游
    -0.27
    沿éĢĶ
    -0.27
    opher
    -0.27
    .Sort
    -0.26
     Survey
    -0.26
     Sort
    -0.26
     sortOrder
    -0.25
    (sort
    -0.25
    POSITIVE LOGITS
    çĬ¯ç½ª
    0.26
     fat
    0.26
     debut
    0.26
    illi
    0.25
    ç»ĨåĪĨ
    0.25
    åĨįçİ°
    0.25
    TeX
    0.25
    ä¹ĥèĩ³
    0.25
    å®īåĢį
    0.24
     solid
    0.24
    Activations Density 0.907%

    No Known Activations