© 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. 162435
    Prev
    Next
    INDEX
    Explanations

    Start of articles

    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
    emption
    -0.30
    otto
    -0.27
    ation
    -0.26
    æ¾Ħ
    -0.26
    <w
    -0.26
    ees
    -0.25
    uces
    -0.25
     Laz
    -0.24
    otch
    -0.24
    PTION
    -0.24
    POSITIVE LOGITS
    éĵĿåIJĪéĩij
    0.26
    enders
    0.24
     saja
    0.24
    åºĦ
    0.24
     pareja
    0.24
     franch
    0.23
     sliding
    0.23
    çij¾
    0.23
    ullah
    0.23
     surely
    0.22
    Activations Density 0.046%

    No Known Activations