© 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. 108337
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
    wald
    -0.26
    åģļåĩº
    -0.26
    åĢĴ
    -0.26
    izzle
    -0.25
    ä¿¡æģ¯
    -0.25
    ведениÑı
    -0.25
    å¿ĥåĬ¨
    -0.25
    ORD
    -0.24
    uptools
    -0.24
     Heard
    -0.24
    POSITIVE LOGITS
    геÑĢ
    0.25
    å¾¼
    0.25
    .runtime
    0.25
    setWidth
    0.24
    åĸľåī§
    0.23
    ached
    0.23
     jorn
    0.23
    @d
    0.23
    inos
    0.23
    .setWidth
    0.23
    Activations Density 0.979%

    No Known Activations