INDEX

Explanations

cart

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

CDs

-0.28

/-

-0.26

åĩºçīĪç¤¾

-0.26

å¦ĤæĦı

-0.25

å®ŀä½ĵ

-0.25

.mar

-0.24

 pare

-0.24

translations

-0.24

æĭ³

-0.24

åľ¨åĽ½å¤ĸ

-0.24

POSITIVE LOGITS

èº«ä»½

0.27

 Ð¾Ð±ÑĬÑıÐ²Ð»

0.27

æĸ°éĹ»ä¸Ńå¿ĥ

0.25

panic

0.25

usan

0.25

_cov

0.24

done

0.24

auen

0.24

.nano

0.24

 reass

0.23

Activations Density 0.001%

cart

No Comments

No Known Activations