© 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. 163465
    Prev
    Next
    INDEX
    Explanations

    Code, research, publications

    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
    å¾ĭ
    -0.28
    wb
    -0.28
    mw
    -0.27
    _Do
    -0.27
     sac
    -0.25
    ¹
    -0.25
    åĮħ
    -0.25
    ãĤĪãģı
    -0.25
    æĬĬèĩªå·±
    -0.24
     ÑģебÑı
    -0.24
    POSITIVE LOGITS
    unday
    0.36
    ulas
    0.27
    anoi
    0.26
    Hyper
    0.26
    inders
    0.26
    Comb
    0.25
     Comb
    0.24
     domina
    0.24
     judgment
    0.24
     Bradley
    0.24
    Activations Density 0.006%

    No Known Activations