INDEX

Explanations

get

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

 under

-0.37

under

-0.27

éĴĪ

-0.26

 Under

-0.26

ding

-0.25

 returns

-0.25

Under

-0.25

è¿Ķ

-0.25

"&#

-0.25

 cheap

-0.25

POSITIVE LOGITS

asurable

0.26

ê²½ìĺģ

0.25

orney

0.25

eor

0.25

 Seal

0.25

 interven

0.25

çłľ

0.25

cpy

0.24

æº¶è§£

0.24

å°ģ

0.24

Activations Density 0.012%

get

No Comments

No Known Activations