© 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. 39822
    Prev
    Next
    INDEX
    Explanations

    punctuation and numbers

    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
    è¯ķ
    -0.30
    æĪijéĥ½
    -0.29
    кÑĢо
    -0.27
    票
    -0.26
    è¿Ļä¸Ģå¹´
    -0.26
    terra
    -0.25
    rawer
    -0.25
    elson
    -0.24
    ochen
    -0.24
    ferred
    -0.24
    POSITIVE LOGITS
     flop
    0.25
    åĮĸçŁ³
    0.24
    uracy
    0.24
    éĤ´
    0.23
    èĻļ
    0.23
    genesis
    0.23
    clide
    0.23
     possible
    0.23
     GÅĤ
    0.22
    çĤ¹äºĨ
    0.22
    Activations Density 0.239%

    No Known Activations