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

veillance

-0.28

imin

-0.27

anine

-0.26

isin

-0.26

bis

-0.26

å±ıéļľ

-0.26

isos

-0.25

ä¸¤åĳ¨

-0.25

gresql

-0.24

.magic

-0.24

POSITIVE LOGITS

æ¶ĤæĬ¹

0.30

æ¶Ĥ

0.26

peare

0.26

(Intent

0.24

çĥĪ

0.24

æĴ¥

0.23

å©´

0.23

 Pour

0.23

 rated

0.23

Pour

0.23

Activations Density 0.025%

No Known Activations

This feature has no known activations.