INDEX

Explanations

complex

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

entin

-0.29

-install

-0.27

icap

-0.26

ens

-0.26

pare

-0.25

 argent

-0.25

Ã¡c

-0.24

æ·®å®ī

-0.24

file

-0.24

äºĴèģĶäºĴéĢļ

-0.24

POSITIVE LOGITS

 tats

0.26

"--

0.26

_UNS

0.26

pany

0.25

ester

0.24

keit

0.24

thane

0.24

_decorator

0.24

osaic

0.23

_Items

0.23

Activations Density 1.819%

complex

No Comments

No Known Activations