© 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. 89061
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åĬ¨æľº
    -0.25
    .SizeType
    -0.24
    ResponseStatus
    -0.24
     sided
    -0.24
    xis
    -0.24
    	ps
    -0.24
     daylight
    -0.24
    URITY
    -0.24
    çŀ©
    -0.24
    æ±Łä¸ľ
    -0.23
    POSITIVE LOGITS
    è´¡
    0.27
    èĩªå¦Ĥ
    0.26
     kald
    0.26
    tober
    0.26
     schn
    0.26
    hydr
    0.26
    å¥¹åľ¨
    0.25
    足以
    0.25
    ampled
    0.25
    å§ĵ
    0.25
    Activations Density 0.031%

    No Known Activations

    This feature has no known activations.