INDEX

Explanations

nan

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æº¯

-0.27

çĶŁåĳ½åĳ¨æľŁ

-0.25

_seek

-0.24

andex

-0.24

 seek

-0.24

 ÑĩÐµÐ¼

-0.23

 lifecycle

-0.23

éĻĲãĤĬ

-0.23

-spe

-0.23

 Experts

-0.23

POSITIVE LOGITS

åĹĳ

0.29

å®ĺ

0.27

CPP

0.25

(--

0.25

æ¸ħåĩī

0.25

sell

0.25

 unnoticed

0.24

ä¸Ģäºĭ

0.24

çĤ¹æ»´

0.23

Ã´m

0.23

Activations Density 0.026%

nan

No Comments

No Known Activations