INDEX

Explanations

comparisons and inequalities

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

jap

-0.29

ìĥµ

-0.27

lat

-0.26

 seri

-0.25

æķĪ

-0.25

hib

-0.24

TOT

-0.24

éĿ¢åħ·

-0.24

Ð¾Ð²Ð°ÑĢ

-0.24

æ¸©æ³ī

-0.24

POSITIVE LOGITS

åĥıæĺ¯

0.30

 McCl

0.28

kea

0.26

 ADVISED

0.25

imeType

0.24

è¿Ľåĩº

0.24

lius

0.24

æĬ¥åĳĬæĺ¾ç¤º

0.24

åıĳå±ķç©ºéĹ´

0.24

å¯¹æĪĳä»¬

0.23

Activations Density 0.012%

comparisons and inequalities

No Comments

No Known Activations