© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 88657
    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_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nip
    -0.31
     nip
    -0.29
    å¿Ĺ
    -0.28
    æĺ¯å¯¹
    -0.27
     contr
    -0.26
    äll
    -0.26
    éĢĴ
    -0.26
    ctor
    -0.26
    âĩĢ
    -0.26
    -license
    -0.25
    POSITIVE LOGITS
    uries
    0.27
    rena
    0.26
    ITIES
    0.25
    ä»»ä½ķ人
    0.25
     readers
    0.24
    ä¸ĩ象
    0.24
     обÑıзаÑĤелÑĮ
    0.24
     Olson
    0.24
    æĥ¬
    0.23
    lü
    0.23
    Activations Density 9.245%

    No Known Activations