INDEX

Explanations

No Explanations Found

New Auto-Interp

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

å¹¶å°Ĩ

-0.27

ighting

-0.26

istik

-0.26

uries

-0.25

ihar

-0.25

ActionResult

-0.25

è©±ãĤĴ

-0.25

ä»ĸä»¬æĺ¯

-0.25

pering

-0.24

 previews

-0.24

POSITIVE LOGITS

{}",

0.34

æģ°æģ°

0.28

{}".

0.28

Lia

0.27

èĲ½

0.26

å¯¹æīĭ

0.26

åĩłä¸ª

0.26

 incons

0.25

æł¼å¼ı

0.25

late

0.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.