INDEX

Explanations

appropriate

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

 crim

-0.28

ä¸ĭå·´

-0.26

ãĥĥãĤ¯ãĤ¹

-0.25

ilda

-0.24

 hope

-0.24

Ð¸Ð·Ð°ÑĨÐ¸Ñı

-0.24

styleType

-0.24

.initState

-0.24

hoa

-0.24

éĵİ

-0.24

POSITIVE LOGITS

_od

0.29

ÑĢÐ¾ÑģÑĤ

0.28

 Advertisement

0.28

od

0.27

oda

0.27

æĦŁæĥħ

0.27

od

0.25

aket

0.25

rop

0.24

ppe

0.24

Activations Density 27.559%

appropriate

No Comments

No Known Activations