© 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. 19-TRANSCODER-HP
    7. 9075
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ersed
    -0.28
    ather
    -0.27
    éºĩ
    -0.26
    åħ¨éĿ¢æİ¨è¿Ľ
    -0.26
    è¿ĽéŨ
    -0.26
     FAC
    -0.25
    illes
    -0.25
     duly
    -0.25
    èĤ¤èī²
    -0.25
     embr
    -0.25
    POSITIVE LOGITS
    arp
    0.29
    座
    0.25
    çĽı
    0.25
    иваниÑı
    0.24
    ót
    0.23
     Ge
    0.23
    éļ§éģĵ
    0.23
     Arsenal
    0.23
    éĻį鼨
    0.23
    åı
    0.23
    Activations Density 0.033%

    No Known Activations