© 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. 163456
    Prev
    Next
    INDEX
    Explanations

    the

    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
     other
    -0.30
    åħ¶ä½Ļ
    -0.29
    ãģĿãģĨãģ§
    -0.29
    çīĻ
    -0.28
    mun
    -0.27
    eten
    -0.27
     diÄŁer
    -0.27
    .other
    -0.26
    åħ¶ä»ĸ
    -0.26
    onth
    -0.25
    POSITIVE LOGITS
     impe
    0.27
    æ®Ĭ
    0.26
    iles
    0.25
    odes
    0.25
    APE
    0.25
    dt
    0.25
    éĿ¢çĽ®
    0.24
    zzo
    0.24
    æĹ©çĤ¹
    0.24
    icon
    0.24
    Activations Density 0.004%

    No Known Activations