© 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. 41199
    Prev
    Next
    INDEX
    Explanations

    Squirrel

    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
    æİ¥
    -0.32
    velle
    -0.28
    ç»°
    -0.27
    å®Įæķ´æĢ§
    -0.27
    缺éĻ·
    -0.27
    å®Įæķ´çļĦ
    -0.26
    åģ¿
    -0.25
    sti
    -0.25
    ä¿®æĶ¹
    -0.25
    tered
    -0.24
    POSITIVE LOGITS
    pora
    0.28
    ì°¨
    0.28
     spotlight
    0.28
    nage
    0.27
     Concurrent
    0.26
    TextNode
    0.25
     hw
    0.25
    çĹ£
    0.24
     tán
    0.24
    æĪı
    0.24
    Activations Density 3.326%

    No Known Activations