INDEX

Explanations

ada

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éĿ¶

-0.28

iales

-0.26

trys

-0.25

æłĳ

-0.25

utsche

-0.25

ument

-0.25

tribution

-0.25

submission

-0.25

çłĸ

-0.24

trib

-0.24

POSITIVE LOGITS

 conflict

0.28

 setInterval

0.26

ä¸īæĸ¹

0.25

Longrightarrow

0.24

è¯Ĺ

0.24

ERC

0.24

æĹ§

0.24

pu

0.24

ÑĩÐµÑģÑĤÐ²Ð¾

0.24

ollections

0.24

Activations Density 0.001%

ada

No Comments

No Known Activations