© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161947
    Prev
    Next
    INDEX
    Explanations

    "360" & numbers ending in 0

    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
    otti
    -0.28
    ä¸įæĢķ
    -0.26
     usefulness
    -0.26
    沫
    -0.25
    olders
    -0.25
    çIJħ
    -0.24
    izons
    -0.24
     closely
    -0.24
    _cmos
    -0.24
    itos
    -0.24
    POSITIVE LOGITS
    Outlet
    0.30
    è¿IJåĬ¨
    0.28
    æİ¥åħ¥
    0.26
    åľī
    0.25
    Everything
    0.25
    gest
    0.25
    ç¼°
    0.25
     rÃłng
    0.25
    FromArray
    0.24
    sky
    0.24
    Activations Density 0.014%

    No Known Activations