© 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. 129311
    Prev
    Next
    INDEX
    Explanations

    Forms of "to be"

    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
    æī©
    -0.29
    èį·åħ°
    -0.27
    åľ¨äº¬
    -0.26
    å®Įåħ¨æ²¡æľī
    -0.26
    ç½®
    -0.26
    积累äºĨ
    -0.25
    è¡Įéķ¿
    -0.24
    æ¯ıå¹´éĥ½
    -0.24
    åIJĮæĹ¶ä¹Ł
    -0.24
    åı£ä¸Ń
    -0.24
    POSITIVE LOGITS
    oe
    0.29
     than
    0.26
    erate
    0.25
    ere
    0.25
    eres
    0.24
    anz
    0.24
    ory
    0.24
     Mor
    0.24
    FA
    0.24
     Carter
    0.24
    Activations Density 0.010%

    No Known Activations