© 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. 162676
    Prev
    Next
    INDEX
    Explanations

    code files

    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
    clude
    -0.28
     souls
    -0.28
    titles
    -0.25
    .generated
    -0.25
    oreach
    -0.23
    æĤ¨å¥½
    -0.23
    arial
    -0.23
    ComputedStyle
    -0.23
    rylic
    -0.23
    ÙĦÙī
    -0.23
    POSITIVE LOGITS
     tagging
    0.26
     Gates
    0.25
     []↵
    0.25
    èĨ»
    0.24
    _phase
    0.24
    song
    0.24
    dere
    0.24
    wright
    0.24
    æłĩçŃ¾
    0.23
     phase
    0.23
    Activations Density 0.000%

    No Known Activations