INDEX

Explanations

instructions

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

ite

-0.30

ITE

-0.29

 Switch

-0.28

switch

-0.26

 switch

-0.26

.isConnected

-0.26

asher

-0.26

ITES

-0.25

alte

-0.25

ITED

-0.25

POSITIVE LOGITS

pch

0.28

 unic

0.28

 conceivable

0.26

olvable

0.26

Knowing

0.25

éĽı

0.25

 Knowing

0.24

 likely

0.24

oping

0.24

 quickest

0.24

Activations Density 0.001%

instructions

No Comments

No Known Activations