© 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. 162441
    Prev
    Next
    INDEX
    Explanations

    catalyst

    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
    主æĿĥ
    -0.27
    plr
    -0.27
    è°ĥçłĶ
    -0.26
    survey
    -0.26
     büt
    -0.26
    ^K
    -0.26
    åħ¼
    -0.25
    éļıä¹ĭ
    -0.25
    _equals
    -0.24
    Survey
    -0.24
    POSITIVE LOGITS
    ized
    0.29
    istic
    0.28
    ry
    0.28
    CAC
    0.28
    eel
    0.28
    istically
    0.27
     catalyst
    0.26
    è²Į
    0.26
    åĮĸ
    0.25
    åĮĸçļĦ
    0.25
    Activations Density 0.269%

    No Known Activations