© 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. 56807
    Prev
    Next
    INDEX
    Explanations

    Incomplete or unrealized things

    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
    æ¢Ĺ
    -0.26
     Dir
    -0.25
    cient
    -0.24
    ject
    -0.24
    utr
    -0.24
     reversible
    -0.24
    马ä¸Ĭ
    -0.24
    åı¯çĶ¨
    -0.24
    chantment
    -0.24
    |h
    -0.23
    POSITIVE LOGITS
     processed
    0.45
    processed
    0.34
     visited
    0.34
     explored
    0.34
     scanned
    0.33
     dealt
    0.32
     treated
    0.32
    åħijçİ°
    0.32
     executed
    0.31
     addressed
    0.31
    Activations Density 0.009%

    No Known Activations