INDEX

Explanations

math problems

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

 Converted

-0.28

éĹ¨æ§Ľ

-0.27

Converted

-0.27

cÃŃ

-0.26

éĹ¨

-0.26

Typed

-0.26

gricult

-0.25

ThreadId

-0.25

chia

-0.24

anded

-0.24

POSITIVE LOGITS

åĳĬ

0.28

roke

0.26

 cáº£nh

0.26

uda

0.26

ucas

0.25

rael

0.25

Ð³Ð¾Ð½

0.24

èī¯

0.24

ige

0.23

Stroke

0.23

Activations Density 0.007%

math problems

No Comments

No Known Activations