© 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. 6473
    Prev
    Next
    INDEX
    Explanations

    confidence

    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
     liv
    -0.29
    社
    -0.28
    ä¸įå¤ļ
    -0.27
    ftime
    -0.26
    èĻIJ
    -0.26
    ppv
    -0.25
    levator
    -0.25
    @qq
    -0.24
    å°±ä¸ļ
    -0.24
    vg
    -0.24
    POSITIVE LOGITS
    åĶ¯
    0.26
    sa
    0.25
    dan
    0.25
    keepers
    0.25
    izo
    0.24
    eda
    0.24
     onPostExecute
    0.24
    è§ģæķĪ
    0.24
    MAT
    0.24
    ulares
    0.24
    Activations Density 0.008%

    No Known Activations