© 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. 22-TRANSCODER-HP
    7. 130228
    Prev
    Next
    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cur
    -0.31
     اÙĦÙĪاØŃد
    -0.25
    _probe
    -0.24
    审
    -0.24
    mission
    -0.24
     verr
    -0.24
     Trou
    -0.23
    æĶ¾è¿ĩ
    -0.23
     cur
    -0.23
     Curt
    -0.22
    POSITIVE LOGITS
    èĥ½å¾ĹåĪ°
    0.28
     intimately
    0.28
    EMA
    0.28
    åı¯è§Ĥ
    0.28
     tighten
    0.27
    ,readonly
    0.26
     schön
    0.26
    tems
    0.26
    uable
    0.26
    èĩ´
    0.25
    Activations Density 0.019%

    No Known Activations