© 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. 40235
    Prev
    Next
    INDEX
    Explanations

    benefit

    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
     objectives
    -0.27
    ponents
    -0.26
    æŨ
    -0.26
    ives
    -0.26
    plex
    -0.26
    åĿĢ
    -0.26
    prises
    -0.25
    å¾Ĵ
    -0.24
    pon
    -0.24
    ue
    -0.24
    POSITIVE LOGITS
    hung
    0.30
    æııåĨĻ
    0.26
    èĩªæŁ¥
    0.26
    jie
    0.26
    å®īçĦ¶
    0.26
    人å±ħ
    0.25
    æĽ´éĢĤåIJĪ
    0.25
    çļĦæľĢä½³
    0.25
    hay
    0.25
    èİ·å¾ĹæĽ´å¤ļ
    0.24
    Activations Density 0.361%

    No Known Activations