INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

days

-0.27

äººå¤§

-0.26

 capit

-0.26

 Fridays

-0.26

ystal

-0.26

è£ħ

-0.25

XE

-0.25

ä¹¾åĿ¤

-0.25

catalog

-0.24

åĻ±

-0.24

POSITIVE LOGITS

 tracer

0.30

mul

0.28

 Redistributions

0.27

.gnu

0.26

ceptors

0.26

 rewind

0.26

ç½ĳ

0.25

 Surround

0.25

tracer

0.25

ynes

0.24

Activations Density 0.000%

No Comments

No Known Activations