© 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. 23-TRANSCODER-HP
    7. 163471
    Prev
    Next
    INDEX
    Explanations

    Object-oriented programming

    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
    eed
    -0.29
    éŃį
    -0.27
    HTTPS
    -0.26
    ping
    -0.26
    -proof
    -0.25
    onet
    -0.25
     pans
    -0.25
     Mour
    -0.24
    wards
    -0.24
    CNN
    -0.24
    POSITIVE LOGITS
    ness
    0.29
    ÑģÑı
    0.26
    Smarty
    0.24
    SION
    0.24
    aje
    0.24
     none
    0.23
    åıĺéĢŁ
    0.23
    æĸ¹å¼ıè¿Ľè¡Į
    0.23
     ARE
    0.23
    systems
    0.23
    Activations Density 0.022%

    No Known Activations