© 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. 6299
    Prev
    Next
    INDEX
    Explanations

    directions

    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
    è¿ijä¹İ
    -0.27
    iques
    -0.26
    åĹĵåŃIJ
    -0.26
     ActionTypes
    -0.25
     vertically
    -0.25
    ä¸įåłª
    -0.23
     Depends
    -0.23
    antz
    -0.23
    -Sep
    -0.23
    è¦ģä¹Ī
    -0.23
    POSITIVE LOGITS
    ugi
    0.26
    ee
    0.26
    ä¹ł
    0.26
    åݻ买
    0.26
     ["
    0.25
     hit
    0.24
     find
    0.24
     conditioning
    0.24
    finding
    0.24
    adoo
    0.24
    Activations Density 0.027%

    No Known Activations