© 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. 111571
    Prev
    Next
    INDEX
    Explanations

    safety, security, performance

    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
    èĭ¦èĭ¦
    -0.28
    çĿģå¼Ģ
    -0.26
    çĻ¾å®¶
    -0.26
    Altern
    -0.24
    inkel
    -0.24
    çĿģ
    -0.24
    åĨľå®¶
    -0.24
    inkle
    -0.24
    yny
    -0.23
    urrence
    -0.23
    POSITIVE LOGITS
    å®īåħ¨
    0.26
    éĺ²çģ«
    0.25
    :])↵
    0.24
     tam
    0.24
     дал
    0.24
     im
    0.24
    æ¢Ĺ
    0.24
     dal
    0.23
     safety
    0.23
     impro
    0.23
    Activations Density 0.028%

    No Known Activations