INDEX

Explanations

technical documents

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ã¼ss

-0.25

æĸ¯é¡¿

-0.25

 newData

-0.25

ENAME

-0.25

 Staten

-0.25

 passed

-0.24

PAS

-0.24

(^)(

-0.24

 West

-0.24

ãĥ¼ãĤ¹

-0.24

POSITIVE LOGITS

urf

0.26

 Beau

0.26

rear

0.25

èĩªåŃ¦

0.25

åĲĬé¡¶

0.25

.bit

0.25

rollable

0.24

æĹłæīĢè°ĵ

0.24

aur

0.24

æŀ¯çĩ¥

0.24

Activations Density 0.001%

technical documents

No Comments

No Known Activations