INDEX

Explanations

childhood or hometown

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

ACK

-0.26

ç»ıåķĨ

-0.26

ergy

-0.26

éŁ³

-0.24

ecycle

-0.24

 acknowledged

-0.24

otate

-0.24

åħ±çĶŁ

-0.23

 acknow

-0.23

 tamp

-0.23

POSITIVE LOGITS

OLER

0.28

æ¼ıæ°´

0.27

 pearls

0.27

Ð»ÐµÑĩ

0.25

æ½ľæ°´

0.25

 Whatever

0.25

.esp

0.25

 domestic

0.25

Ð¾Ð¼Ð½

0.24

Memo

0.24

Activations Density 0.783%

childhood or hometown

No Comments

No Known Activations