INDEX

Explanations

Department

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

 maiden

-0.30

known

-0.28

 known

-0.26

esus

-0.26

ç®¡çĲĨå·¥ä½ľ

-0.25

Reflect

-0.25

 realities

-0.24

 provinc

-0.24

äºĨèµ·æĿ¥

-0.24

ç®Ĺ

-0.23

POSITIVE LOGITS

ktor

0.32

endir

0.26

 ObjectOutputStream

0.24

Ĭ¶æĢģ

0.24

acency

0.24

Ø±Ø³

0.24

æĮĤåľ¨

0.24

ç¥¨

0.23

ãģĦãģªãģĦ

0.23

WB

0.23

Activations Density 0.001%

Department

No Comments

No Known Activations