INDEX

Explanations

accreditation

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

(prop

-0.28

ework

-0.28

prop

-0.28

erving

-0.27

Ð¸ÑĤÐ°

-0.26

props

-0.26

Prop

-0.25

attro

-0.25

 PROP

-0.25

æ²Ļæ¼ł

-0.25

POSITIVE LOGITS

ilogy

0.29

 contracting

0.28

owo

0.26

ctp

0.26

 detain

0.26

åĲĪèµĦ

0.25

Sr

0.25

robe

0.24

ä¾¯

0.24

æĢ»éĺŁ

0.24

Activations Density 0.233%

accreditation

No Comments

No Known Activations