INDEX

Explanations

Food, specifically meat

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tro

-0.31

å½¼å¾Ĺ

-0.31

ãĥĪ

-0.25

tro

-0.25

 micro

-0.25

otes

-0.25

op

-0.25

Micro

-0.24

 Micro

-0.24

 supply

-0.24

POSITIVE LOGITS

ãģĮãĤī

0.28

ANGES

0.27

ä¼Ł

0.25

Ã¤Ã¤n

0.25

èģĶåĬ¨

0.24

åī§çĥĪ

0.24

åİĨåı²

0.24

puties

0.24

 manned

0.24

uffy

0.23

Activations Density 0.015%

Food, specifically meat

No Comments

No Known Activations