© 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. 129476
    Prev
    Next
    INDEX
    Explanations

    up

    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
    bah
    -0.27
    ä¸ĥåħ«
    -0.25
     Chart
    -0.25
    åľºåľ°
    -0.25
    rschein
    -0.25
     Schiff
    -0.25
    æĶ¾è¿ĩ
    -0.25
    å¨Ł
    -0.24
    èµ°è¿ĩ
    -0.23
    Spo
    -0.23
    POSITIVE LOGITS
    enger
    0.30
    contentType
    0.29
    è¤
    0.28
    èĥĨåĽºéĨĩ
    0.27
     secrets
    0.26
    ignant
    0.25
    é«ĺæķĪçļĦ
    0.25
    ools
    0.25
     notation
    0.24
    contents
    0.24
    Activations Density 0.002%

    No Known Activations