© 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. 27-TRANSCODER-HP
    7. 8275
    Prev
    Next
    INDEX
    Explanations

    metastasis and cancer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PURE
    -0.27
    室åĨħ
    -0.26
     khẩu
    -0.26
    èŃ·
    -0.25
    åį·
    -0.25
    عÙĨ
    -0.25
    creativecommons
    -0.24
    PACE
    -0.24
    éĢĴç»Ļ
    -0.24
    /mit
    -0.24
    POSITIVE LOGITS
     settling
    0.80
     settle
    0.77
     settled
    0.71
     settlement
    0.67
     settles
    0.65
     Settlement
    0.60
    sett
    0.60
     settlements
    0.59
    å®ļå±ħ
    0.56
    æīİæł¹
    0.49
    Activations Density 0.013%

    No Known Activations