© 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. 24920
    Prev
    Next
    INDEX
    Explanations

    the/of

    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
     freely
    -0.28
    ä¿Ŀéļľ
    -0.27
    å°Ħ
    -0.27
     figure
    -0.25
     Gut
    -0.24
    åĵªäºĽ
    -0.24
    æĻ®
    -0.24
    atra
    -0.23
    ow
    -0.23
     Rach
    -0.23
    POSITIVE LOGITS
    éĢ¢
    0.27
    çħ
    0.26
    ichtig
    0.25
    YSTEM
    0.25
    entr
    0.24
    pll
    0.24
    åħ³èĬĤ
    0.23
     Pentagon
    0.23
    TimeZone
    0.23
     préc
    0.23
    Activations Density 0.001%

    No Known Activations