INDEX

Explanations

purpose

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

edia

-0.32

ged

-0.27

éģĹ

-0.26

ä¿ĿçķĻ

-0.25

åīĤ

-0.25

å¸¸æĢģ

-0.25

Sorting

-0.25

æľīæķĪ

-0.24

 select

-0.24

æĢģ

-0.24

POSITIVE LOGITS

 Civic

0.28

Lens

0.25

PING

0.25

ighborhood

0.24

licas

0.24

Lon

0.24

 Upon

0.24

 Ð¿ÐµÑĢÐµÐ²Ð¾Ð´

0.24

º«

0.24

asn

0.24

Activations Density 0.010%

purpose

No Comments

No Known Activations