INDEX

Explanations

in

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

TIME

-0.27

 translate

-0.27

enate

-0.26

åĢŁ

-0.25

tober

-0.25

èŃ¦

-0.24

elry

-0.24

types

-0.24

 dive

-0.24

Rotate

-0.24

POSITIVE LOGITS

aston

0.28

idth

0.26

 Grain

0.25

æĹ¶å°ļ

0.25

 getArguments

0.25

 Differential

0.24

createClass

0.24

(('

0.23

 HELP

0.23

 Bald

0.23

Activations Density 0.002%

in

No Comments

No Known Activations