© 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. 97739
    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
    du
    -0.29
    å¥ļ
    -0.26
    èĻ±
    -0.25
     enlisted
    -0.25
     right
    -0.25
     sitting
    -0.25
    Psi
    -0.24
    æĬķåħ¥ä½¿çĶ¨
    -0.24
    åı³è¾¹
    -0.24
    åĸª
    -0.24
    POSITIVE LOGITS
    çĤ¼
    0.30
    otland
    0.28
    bearing
    0.26
    éĻĮçĶŁ
    0.26
    åŀĭä¼ģä¸ļ
    0.26
    algo
    0.25
    dato
    0.25
    ophilia
    0.25
     stems
    0.24
    **č↵
    0.24
    Activations Density 0.009%

    No Known Activations