© 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. 19-TRANSCODER-HP
    7. 5905
    Prev
    Next
    INDEX
    Explanations

    Legal documents and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conven
    -0.30
    褥
    -0.26
     closely
    -0.26
     VE
    -0.25
    åķ¬
    -0.25
    arts
    -0.24
    ativo
    -0.24
     training
    -0.23
     scrutin
    -0.23
    èѬ
    -0.23
    POSITIVE LOGITS
    ews
    0.28
    ewe
    0.27
    еÑĩ
    0.27
    mont
    0.26
    ycz
    0.26
    å¾ģ
    0.25
     Zusammen
    0.25
    æĶ¯æŀ¶
    0.25
    å§Ķåijĺ
    0.25
    âĩ©
    0.24
    Activations Density 0.001%

    No Known Activations