© 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. 163201
    Prev
    Next
    INDEX
    Explanations

    leadership positions

    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
     or
    -0.26
    è§ī
    -0.25
    fdf
    -0.25
    æĭ£
    -0.24
    c
    -0.24
    Qual
    -0.24
    å§ĵåIJį
    -0.24
     XP
    -0.23
     A
    -0.23
    d
    -0.23
    POSITIVE LOGITS
    夫人
    0.27
    apsed
    0.27
    ements
    0.27
     ünlü
    0.27
    ventus
    0.25
    acie
    0.25
    ermen
    0.25
    PointerType
    0.25
    ussen
    0.25
    acters
    0.25
    Activations Density 0.016%

    No Known Activations