INDEX

Explanations

as

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

lix

-0.31

 themselves

-0.30

è¿ĳ

-0.29

åħŃåįģ

-0.29

åĲĦèĩª

-0.29

è½®æµģ

-0.28

æ³Ľ

-0.26

rtype

-0.25

interopRequireDefault

-0.25

æľīä¸Ģå®ļ

-0.25

POSITIVE LOGITS

Released

0.26

anine

0.25

hy

0.25

 depart

0.25

 Became

0.24

 Sherman

0.24

is

0.23

ipay

0.23

 became

0.23

mes

0.23

Activations Density 0.009%

as

No Comments

No Known Activations