INDEX

Explanations

ley

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĿ¡ä»¶

-0.30

 Alma

-0.28

 conditions

-0.28

conditions

-0.27

 lives

-0.25

 condition

-0.25

 Mort

-0.25

eba

-0.24

 Ruth

-0.24

	controller

-0.23

POSITIVE LOGITS

æĥ³ä¸įåĪ°

0.30

_COLL

0.25

åĨįä¹Łæ²¡æľī

0.25

-sizing

0.25

ENDER

0.25

jiang

0.24

é²¨

0.24

æ¬ł

0.24

/fw

0.24

å¨¼

0.24

Activations Density 0.002%

ley

No Comments

No Known Activations