INDEX

Explanations

code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éģĵå£«

-0.28

 Thursday

-0.28

Thu

-0.27

åįģåĽĽæĿ¡

-0.27

èĥ´

-0.26

.ra

-0.25

 spans

-0.25

aklÄ±

-0.25

Thu

-0.25

æ¯¡

-0.25

POSITIVE LOGITS

ç«ĸ

0.30

çĸĳä¼¼

0.27

ä»ĸä»¬ä¼ļ

0.27

atus

0.26

,application

0.26

Mix

0.25

 Ethi

0.25

å¼¯

0.24

 fifth

0.24

bucks

0.24

Activations Density 1.036%

code

No Comments

No Known Activations