INDEX

Explanations

executives

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

æĪĸèĢħåħ¶ä»ĸ

-0.26

ains

-0.26

front

-0.25

shift

-0.25

ê³Ħ

-0.24

åħ

-0.24

(slice

-0.24

æİ¢

-0.24

ped

-0.23

_driver

-0.23

POSITIVE LOGITS

upe

0.28

éĹŃ

0.28

SURE

0.28

GD

0.25

SG

0.25

_GF

0.25

eut

0.25

åĲĦä¸ªæĸ¹éĿ¢

0.24

ULA

0.24

OG

0.24

Activations Density 0.002%

executives

No Comments

No Known Activations