© 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. 8657
    Prev
    Next
    INDEX
    Explanations

    environmental issues

    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
    éļ¶
    -0.27
    è¾ĥ大çļĦ
    -0.25
    ä¾µèļĢ
    -0.25
    ä¸ĭ游
    -0.25
     Reserve
    -0.25
     reserve
    -0.24
    ·»
    -0.24
    é¡¹çĽ®çļĦ
    -0.24
    管çIJĨä¸Ńå¿ĥ
    -0.24
     reserves
    -0.24
    POSITIVE LOGITS
    isp
    0.28
    attend
    0.28
    iasm
    0.28
    ogram
    0.27
     atmosphere
    0.26
     ISP
    0.26
    æ°ĶåĢĻ
    0.26
    isy
    0.25
    proof
    0.25
    (Cl
    0.25
    Activations Density 0.000%

    No Known Activations