© 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. 23-TRANSCODER-HP
    7. 25120
    Prev
    Next
    INDEX
    Explanations

    tight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įçĦ¶
    -0.31
    SY
    -0.27
    èĮ¸
    -0.26
    éĤ¨
    -0.26
    JR
    -0.25
    apult
    -0.25
    hall
    -0.25
    ç¨Ķ
    -0.24
    consume
    -0.24
    æ²¹èĢĹ
    -0.24
    POSITIVE LOGITS
     restrictions
    0.30
    ç´§
    0.28
     tight
    0.28
     restriction
    0.27
     Tight
    0.27
     tightening
    0.27
     tighten
    0.27
    angling
    0.26
    tight
    0.26
    æĤ¬
    0.26
    Activations Density 0.030%

    No Known Activations