INDEX

Explanations

burns and ablation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

__$

-0.28

Ð¾ÑģÑĮ

-0.28

asin

-0.28

è¯ģåĪ¸æĬķèµĦ

-0.27

íİ¸

-0.26

[ID

-0.25

çľŁåģĩ

-0.25

hread

-0.25

Æ¡i

-0.25

è´«è¡Ģ

-0.24

POSITIVE LOGITS

åĪº

0.33

åīĮ

0.31

 Copyright

0.28

cid

0.26

 implemented

0.25

WA

0.25

 Proud

0.25

WA

0.25

atat

0.25

adi

0.25

Activations Density 0.851%

burns and ablation

No Comments

No Known Activations