INDEX

Explanations

secrecy or privacy

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anter

-0.32

bia

-0.31

hoot

-0.27

Ð±Ð¾Ð¹

-0.27

entimes

-0.27

.del

-0.27

èĩªåĪ¶

-0.26

acey

-0.26

andum

-0.26

à¸Ķà¸³

-0.25

POSITIVE LOGITS

æĮ¡

0.27

ä¸¤çĤ¹

0.27

(acc

0.26

 distrust

0.25

ExecutionContext

0.25

Argb

0.25

Cit

0.25

 Cent

0.25

æĨĻ

0.25

compat

0.25

Activations Density 0.018%

secrecy or privacy

No Comments

No Known Activations