© 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. 89085
    Prev
    Next
    INDEX
    Explanations

    light

    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
    âİ£
    -0.28
    ÑģÑĤвенно
    -0.28
    iginal
    -0.27
    кла
    -0.26
    /ref
    -0.26
    ascal
    -0.26
    lug
    -0.25
    [at
    -0.25
    SA
    -0.24
     maxx
    -0.24
    POSITIVE LOGITS
    ä¸Ģ级
    0.27
    -tier
    0.26
    otec
    0.26
     unknown
    0.26
    _tools
    0.26
    otre
    0.24
    轩
    0.24
    ot
    0.24
    -scripts
    0.24
    rams
    0.23
    Activations Density 9.009%

    No Known Activations