INDEX

Explanations

le

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

æ¶ĤæĬ¹

-0.29

 forall

-0.28

tower

-0.27

 expressly

-0.27

 screwed

-0.26

 utterly

-0.25

 efficiencies

-0.24

_macros

-0.24

åĨ¶éĩĳ

-0.24

 sourceMappingURL

-0.24

POSITIVE LOGITS

 lakes

0.27

lands

0.27

ç²Ĺ

0.27

aw

0.26

raq

0.26

iring

0.26

 Tribe

0.26

á»Ļi

0.25

æĢ¥

0.25

dip

0.25

Activations Density 0.000%

le

No Comments

No Known Activations