INDEX

Explanations

separation and disorganization

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

å¾Īå®¹æĺĵ

-0.26

æ·±åİļçļĦ

-0.26

 concise

-0.25

ä¸Ģæł¹

-0.25

REE

-0.25

ets

-0.25

åı¦ä¸Ģè¾¹

-0.25

å¯Įè£ķ

-0.24

aurus

-0.23

 Charl

-0.23

POSITIVE LOGITS

iÃ«

0.30

orra

0.28

éģĶ

0.28

 Ð³Ð¾ÑĢ

0.27

mount

0.25

é¸¦

0.25

toolbox

0.25

 PageInfo

0.25

éĢħ

0.24

salt

0.24

Activations Density 6.451%

separation and disorganization

No Comments

No Known Activations