INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

{}:

-0.26

holes

-0.26

ieties

-0.26

 Crash

-0.25

 crashing

-0.25

ÑģÑĤÐ²Ñĥ

-0.24

ocrates

-0.24

FAILURE

-0.24

å¼¼

-0.24

MIT

-0.24

POSITIVE LOGITS

éħ¿éħĴ

0.28

ä¸¾

0.27

èĪĮå¤´

0.26

çŃĶåį·

0.26

tep

0.25

 Speech

0.25

oru

0.25

vÃŃ

0.24

åĽŀåİ»

0.24

èĽĬ

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.