INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

à¹Īà¸²à¸ĩ

-0.28

agr

-0.28

[frame

-0.27

ä¸ĢæĬĬ

-0.27

StateException

-0.27

ëĿ½

-0.27

GR

-0.25

(getClass

-0.25

å¹´å¤ľ

-0.25

rokes

-0.25

POSITIVE LOGITS

patches

0.27

Sul

0.25

æĮ¹

0.25

sh

0.25

éĩįå»º

0.25

æĢ¥æķĳ

0.25

 appealed

0.25

 reconstruct

0.24

kee

0.24

 rebuilding

0.24

Activations Density 0.316%

No Comments

No Known Activations