INDEX

Explanations

scam

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

è¶Ĭ

-0.26

ther

-0.26

cket

-0.25

 histor

-0.25

oi

-0.25

me

-0.25

SAM

-0.24

aling

-0.24

uk

-0.23

(-

-0.23

POSITIVE LOGITS

è¯»åĲİ

0.29

GetType

0.27

Msp

0.27

ToFront

0.27

èľķ

0.26

awns

0.25

èĬ±çĵ£

0.25

 dÃ©c

0.25

IONS

0.24

éªļæī°

0.24

Activations Density 39.724%

scam

No Comments

No Known Activations