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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5750
    Prev
    Next
    INDEX
    Explanations

    Relating to others

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    äºĴ
    -0.28
    alysis
    -0.27
    plements
    -0.27
    zsche
    -0.27
    åĩĨæŶ
    -0.26
    isy
    -0.25
    pth
    -0.25
    è½½
    -0.25
    coli
    -0.25
     Suitable
    -0.24
    POSITIVE LOGITS
     reckon
    0.26
    ä¸Ģå¾ĭ
    0.26
     reck
    0.26
    iams
    0.25
    ãĤ¬ãĥ³
    0.24
    ucked
    0.24
     '**
    0.24
    ç±³å°Ķ
    0.24
    èij¬
    0.24
    .override
    0.24
    Activations Density 0.006%

    No Known Activations