© 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. 40695
    Prev
    Next
    INDEX
    Explanations

    names or code

    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
    çĦ¶æĺ¯
    -0.27
    ató
    -0.26
    vs
    -0.25
    unj
    -0.24
    /how
    -0.24
    循
    -0.24
    ismo
    -0.24
    .vars
    -0.23
     verd
    -0.23
    CodeAt
    -0.23
    POSITIVE LOGITS
    æĢĢ
    0.28
    åĬłå·¥
    0.26
    åijĪçİ°
    0.25
     specializing
    0.24
    祢
    0.24
    _GRP
    0.24
    æĶ¶æĭ¾
    0.24
    fried
    0.23
    .proc
    0.23
     processed
    0.23
    Activations Density 0.126%

    No Known Activations