INDEX

Explanations

adjectives and adverbs

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

åĬĽè¿ĺæĺ¯

-0.33

)|(

-0.28

[C

-0.27

,C

-0.25

retain

-0.25

_longitude

-0.25

 Jordan

-0.25

¡´

-0.24

rough

-0.24

hour

-0.24

POSITIVE LOGITS

é¹«

0.25

åİĮ

0.25

èĿ¼

0.24

overn

0.24

elial

0.24

maj

0.24

.AutoComplete

0.24

Ð½ÐµÐ¹

0.24

ensus

0.23

 Barcl

0.23

Activations Density 0.001%

adjectives and adverbs

No Comments

No Known Activations