INDEX

Explanations

Murphy

np_max-act · gemini-2.0-flash

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

hal

-0.31

Hal

-0.28

Ø§Ø¦Ùħ

-0.26

_TOPIC

-0.26

noinspection

-0.26

TA

-0.26

.qq

-0.25

atri

-0.25

Hal

-0.25

.telegram

-0.25

POSITIVE LOGITS

 agency

0.29

åį°

0.28

ordo

0.27

çĲĨäºĭéķ¿

0.27

elah

0.26

ILLS

0.26

MLE

0.25

éĥ¨éķ¿

0.25

.Alignment

0.25

 cotton

0.25

Activations Density 0.003%

Murphy

No Comments

No Known Activations