INDEX

Explanations

of

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.biz

-0.29

"""↵↵↵

-0.29

 airst

-0.27

æĬ¥åĳĬæĺ¾ç¤º

-0.27

ì¹ł

-0.27

"""č↵č↵

-0.26

."↵↵↵

-0.26

cur

-0.25

èĥĥèĤł

-0.25

éĨĭ

-0.25

POSITIVE LOGITS

ALS

0.29

ppy

0.28

stadt

0.28

×¤×§

0.25

leton

0.25

ahoma

0.25

-sk

0.25

ics

0.25

-season

0.24

 profil

0.24

Activations Density 0.000%

of

No Comments

No Known Activations