© 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. 97602
    Prev
    Next
    INDEX
    Explanations

    natural

    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
    çĦ°
    -0.29
    æĥ¬
    -0.27
    èĬ¥
    -0.26
    áºŃn
    -0.25
    verse
    -0.25
    yg
    -0.25
    ette
    -0.25
    媳
    -0.24
    åī¯ç§ĺ书éķ¿
    -0.24
    transform
    -0.24
    POSITIVE LOGITS
    alien
    0.29
    /colors
    0.27
     Ive
    0.26
     beats
    0.26
    ROID
    0.24
    alli
    0.24
    ISON
    0.24
    edBy
    0.24
    以åīį
    0.24
    ä¹ĭåīįçļĦ
    0.24
    Activations Density 0.020%

    No Known Activations