© 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. 108667
    Prev
    Next
    INDEX
    Explanations

    weary

    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
    alsy
    -0.31
    éro
    -0.30
    ual
    -0.29
    ughs
    -0.28
    enberg
    -0.27
    еÑĢиал
    -0.27
    urally
    -0.26
    earer
    -0.26
    ually
    -0.26
    ral
    -0.25
    POSITIVE LOGITS
    åĪ»
    0.33
     nature
    0.29
    ANA
    0.27
     Nature
    0.24
    èŁł
    0.24
     Tud
    0.24
    æĬ¬
    0.24
    åŃ
    0.23
    /sm
    0.23
    è¢Ĵ
    0.23
    Activations Density 0.073%

    No Known Activations