INDEX

Explanations

Technical writing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

Ð½Ð¸Ð·

-0.32

 undermin

-0.30

Ð½Ð¾Ð¼

-0.30

çĢĳ

-0.28

ischer

-0.27

ÑĢÐ¾Ð¼

-0.26

Ð¼Ð¾

-0.26

Ð´Ð°

-0.26

ÙĦÙĬÙģ

-0.26

ëł¹

-0.26

POSITIVE LOGITS

 taken

0.28

Ð¿ÑĢÐ¾ÑĦÐµÑģÑģÐ¸Ð¾Ð½Ð°Ð»

0.26

 prime

0.26

 passages

0.26

ewise

0.25

 according

0.25

 synthesized

0.25

 Polish

0.25

.cz

0.25

 dimension

0.25

Activations Density 0.033%

Technical writing

No Comments

No Known Activations