© 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. 22-TRANSCODER-HP
    7. 112507
    Prev
    Next
    INDEX
    Explanations

    Mont

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ged
    -0.29
    çļ¿
    -0.27
    led
    -0.27
    å«©
    -0.27
    hood
    -0.26
    plied
    -0.25
    gest
    -0.25
    gin
    -0.24
    logue
    -0.24
    venue
    -0.23
    POSITIVE LOGITS
    s
    0.43
    al
    0.33
    ieri
    0.32
    gomery
    0.28
    i
    0.28
    SetValue
    0.27
    erior
    0.24
    sie
    0.24
    ourage
    0.24
    spl
    0.23
    Activations Density 0.280%

    No Known Activations