© 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. 14-TRANSCODER-HP
    7. 40265
    Prev
    Next
    INDEX
    Explanations

    Uncertainty/negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ł
    -0.27
    åı£
    -0.26
    hall
    -0.25
    mitt
    -0.24
    æ±īåł¡
    -0.24
    çĶ·å¥³
    -0.24
    çIJĨæĻº
    -0.24
    稽
    -0.24
    ÑĢод
    -0.23
    æį
    -0.23
    POSITIVE LOGITS
    outer
    0.26
    OTHER
    0.26
    oused
    0.26
    otros
    0.26
    aders
    0.25
    imonials
    0.25
    adoop
    0.25
     Saves
    0.24
    .outer
    0.24
    Outer
    0.24
    Activations Density 0.123%

    No Known Activations