© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161632
    Prev
    Next
    INDEX
    Explanations

    cannot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yw
    -0.27
    ä¸įå¾Ĺå·²
    -0.25
    æľīå¿ħè¦ģ
    -0.25
     permitted
    -0.25
    enu
    -0.25
    å¿ħéľĢ
    -0.24
    gue
    -0.24
     überhaupt
    -0.24
     evacuation
    -0.24
    ä¸ĭæīĭ
    -0.24
    POSITIVE LOGITS
    stein
    0.27
    igan
    0.26
    adar
    0.26
    .sourceforge
    0.24
    æĸ°åĬł
    0.24
    agment
    0.24
    translations
    0.23
    sume
    0.23
    oes
    0.23
     disproportion
    0.23
    Activations Density 0.008%

    No Known Activations