© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7471
    Prev
    Next
    INDEX
    Explanations

    alone

    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
    bbing
    -0.26
    bed
    -0.25
     definite
    -0.24
    berman
    -0.23
    anus
    -0.23
    tere
    -0.23
     trif
    -0.22
    las
    -0.22
    ted
    -0.22
     definitely
    -0.22
    POSITIVE LOGITS
     Honest
    0.23
    åħĴ
    0.23
    stance
    0.23
    ä¸į解
    0.23
    -inst
    0.22
     accord
    0.22
     Retirement
    0.21
     apart
    0.21
     plunge
    0.21
    rnd
    0.21
    Activations Density 2.161%

    No Known Activations