© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6121
    Prev
    Next
    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĪª
    -0.27
    's
    -0.24
     key
    -0.24
    _kv
    -0.23
    .$.
    -0.23
    è¡ĮæĶ¿æľºåħ³
    -0.23
    imonial
    -0.23
     grain
    -0.23
    å±Ģ
    -0.23
    ucz
    -0.22
    POSITIVE LOGITS
    è°Ģ
    0.24
    afone
    0.24
    çħ§æł·
    0.24
    ingle
    0.24
    _INC
    0.24
     Olympia
    0.23
    accepted
    0.23
     hype
    0.23
    Ahead
    0.23
    ħ§
    0.23
    Activations Density 0.197%

    No Known Activations