© 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. 130040
    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_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
    еÑĢж
    -0.26
    éģŀ
    -0.25
    åĢ¾
    -0.25
    æĺ§
    -0.24
    &
    -0.24
    ursive
    -0.24
    @
    -0.24
    contents
    -0.24
    `
    -0.24
     denom
    -0.24
    POSITIVE LOGITS
    reet
    0.32
    ÅĤow
    0.30
    reen
    0.29
    ecute
    0.26
    REEN
    0.26
     Baths
    0.25
    .CV
    0.25
     melts
    0.25
    aura
    0.25
    isque
    0.24
    Activations Density 0.003%

    No Known Activations