INDEX

Explanations

possessive pronoun "our"

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

éĴ¹

-0.30

æ»¡è¶³

-0.28

ç»ĻæĤ¨

-0.27

.pitch

-0.26

tesy

-0.25

/operators

-0.25

çľĭä¸Ģçľĭ

-0.25

à¨¯

-0.24

åĲ¯åıĳ

-0.24

åĲĮæĥħ

-0.24

POSITIVE LOGITS

[at

0.29

 astro

0.27

opensource

0.27

adge

0.26

ajes

0.26

 edged

0.26

OSH

0.24

 pure

0.24

åĽŃ

0.24

 Individual

0.24

Activations Density 0.000%

possessive pronoun "our"

No Comments

No Known Activations