INDEX

Explanations

try, re

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

shaw

-0.28

enko

-0.28

åħ¨å¸Ĥ

-0.27

ptive

-0.26

 dÃ©m

-0.25

_FP

-0.25

iks

-0.25

ä¸įå¼Ģ

-0.24

å¯¼åĲĳ

-0.24

 ways

-0.23

POSITIVE LOGITS

åĨįæ¬¡

0.93

 again

0.79

éĩįæĸ°

0.76

åĨįåº¦

0.76

again

0.73

åĨįæĿ¥

0.72

 Again

0.69

åĨį

0.68

 repeat

0.66

 retry

0.64

Activations Density 0.008%

try, re

No Comments

No Known Activations