© 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. 14-TRANSCODER-HP
    7. 41321
    Prev
    Next
    INDEX
    Explanations

    Leaves/containing "ff"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ooled
    -0.27
    éļIJèĶ½
    -0.27
    åŁºç¡Ģ
    -0.27
    oble
    -0.25
    emente
    -0.25
     concealed
    -0.24
     conven
    -0.24
     pooled
    -0.23
    æģ¯æģ¯
    -0.23
    ÑĦоÑĢ
    -0.23
    POSITIVE LOGITS
    dump
    0.28
    æ³ģ
    0.26
    endar
    0.26
     mun
    0.25
    å¹¿æ³Ľ
    0.24
    vy
    0.24
    åºļ
    0.24
    dition
    0.24
    bell
    0.24
    ç´Ĭä¹±
    0.23
    Activations Density 0.177%

    No Known Activations