© 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. 33-TRANSCODER-HP
    7. 54429
    Prev
    Next
    INDEX
    Explanations

    Meat/Crime related texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ote
    -0.26
     dare
    -0.26
     rem
    -0.26
    åı£æ°Ķ
    -0.26
    é¼ĵ
    -0.26
     G
    -0.25
     R
    -0.25
    ira
    -0.24
    rokes
    -0.24
     prism
    -0.24
    POSITIVE LOGITS
    kus
    0.39
    äºĴéĢļ
    0.29
    bing
    0.28
    holm
    0.28
    ingle
    0.27
    Owners
    0.26
     OWNER
    0.26
    Observers
    0.25
     Methods
    0.25
    bih
    0.25
    Activations Density 0.006%

    No Known Activations