INDEX

Explanations

a

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

 bond

-0.27

 cher

-0.26

bac

-0.26

æīĢè°ĵçļĦ

-0.26

 signature

-0.25

.func

-0.25

 Gazette

-0.25

bac

-0.25

igated

-0.25

çĪ±åĽ½

-0.25

POSITIVE LOGITS

addTo

0.28

apia

0.26

æĺ¯éŁ©åĽ½

0.26

 fres

0.26

ardo

0.25

åĿ¨

0.25

 newPos

0.25

Nil

0.24

thood

0.24

 hacks

0.24

Activations Density 0.004%

a

No Comments

No Known Activations