INDEX

Explanations

governor

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

æľīå¹¸

-0.28

paced

-0.28

Hop

-0.28

fortunate

-0.28

 vant

-0.27

orias

-0.25

Hop

-0.25

nev

-0.25

è¢±

-0.24

çīĿ

-0.24

POSITIVE LOGITS

ule

0.28

ware

0.28

çĻ¾å§ĵ

0.26

0.25

/rules

0.25

ulet

0.24

uls

0.24

care

0.24

isk

0.23

ãģ¾ãģ¨

0.23

Activations Density 0.002%

governor

No Comments

No Known Activations