INDEX

Explanations

Son

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä»Ĭå¹´

-0.29

iteur

-0.26

çĽ®çļĦ

-0.25

åįļ

-0.25

çļĦçĽ®çļĦ

-0.25

åĨįçİ°

-0.25

 complication

-0.24

PUB

-0.24

_misc

-0.24

ioneer

-0.24

POSITIVE LOGITS

 taps

0.28

.Inst

0.27

emp

0.26

è£ħåį¸

0.25

ells

0.25

 belonged

0.25

æ¼ıæ°´

0.25

sel

0.25

 empowered

0.25

 drinks

0.25

Activations Density 0.004%

Son

No Comments

No Known Activations