INDEX

Explanations

Names

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

KHR

-0.28

ENE

-0.27

why

-0.27

roups

-0.27

why

-0.27

ITED

-0.26

 surg

-0.25

æŁ°

-0.25

 regress

-0.25

adj

-0.24

POSITIVE LOGITS

 Colon

0.29

æ¢Ĩ

0.25

Ð»Ð¾Ð¶ÐµÐ½

0.25

colon

0.25

 colonization

0.25

 Faction

0.24

å¤ĩæĪĺ

0.24

æ¼ł

0.24

íĥľ

0.24

requ

0.24

Activations Density 0.005%

Names

No Comments

No Known Activations