INDEX

Explanations

in

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

 WebClient

-0.24

à°¤

-0.24

 Huckabee

-0.24

&S

-0.24

_$

-0.23

åģļä¸įåĪ°

-0.23

 [&](

-0.23

 triples

-0.22

WV

-0.22

ussed

-0.22

POSITIVE LOGITS

 REVIEW

0.30

 Einstein

0.29

QUE

0.27

åĪĨäº«

0.27

çĽ

0.27

AVR

0.26

 maker

0.25

åħ¶æīĢ

0.25

IRQ

0.25

leur

0.25

Activations Density 0.001%

in

No Comments

No Known Activations