© 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. 18-TRANSCODER-HP
    7. 88880
    Prev
    Next
    INDEX
    Explanations

    Mixed content/excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åľ¨åħ¶
    -0.26
    ENOMEM
    -0.26
    radio
    -0.26
    member
    -0.25
    æ®ĸ
    -0.25
    åĵº
    -0.25
    ä¸įå®Į
    -0.24
    ario
    -0.24
    kich
    -0.24
    æĺŁç©º
    -0.24
    POSITIVE LOGITS
    ãģĤãģŁãĤĬ
    0.26
    åĵģ
    0.24
    dump
    0.24
    ordo
    0.24
    oor
    0.24
    isten
    0.24
    die
    0.24
    iven
    0.24
     dup
    0.24
    è¿ĻæŶåĢĻ
    0.24
    Activations Density 6.463%

    No Known Activations