© 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. 6164
    Prev
    Next
    INDEX
    Explanations

    News articles

    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
    è¾¾
    -0.29
    nings
    -0.28
    ätt
    -0.27
     kullanım
    -0.25
    veau
    -0.25
    ainment
    -0.25
    å¾¹
    -0.25
    ning
    -0.25
    amo
    -0.24
    éģĶ
    -0.24
    POSITIVE LOGITS
    Separated
    0.29
    elder
    0.27
    è½Ń
    0.26
    IEW
    0.25
     encoded
    0.25
     visc
    0.25
     mou
    0.24
    MBED
    0.24
    eld
    0.24
    交éĻħ
    0.23
    Activations Density 0.027%

    No Known Activations