© 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. 89933
    Prev
    Next
    INDEX
    Explanations

    have

    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
    thy
    -0.30
    çİ°éĺ¶æ®µ
    -0.27
    Äĩi
    -0.26
    ty
    -0.25
    lse
    -0.24
    ën
    -0.24
    ASH
    -0.24
    æĭ£
    -0.24
    åݿ级
    -0.23
    anse
    -0.23
    POSITIVE LOGITS
     reportedly
    0.28
    htag
    0.25
    wap
    0.25
    ’t
    0.25
    æĪĸå°Ĩ
    0.25
    èĨ¨
    0.25
    ç¡®åĪĩ
    0.24
    EMAIL
    0.24
     undoubtedly
    0.23
    LayoutManager
    0.23
    Activations Density 89.813%

    No Known Activations