INDEX

Explanations

a

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

achts

-0.27

-caret

-0.25

/tcp

-0.25

ä½ľçī©

-0.25

ilater

-0.25

<footer

-0.24

atchet

-0.24

äº¹

-0.23

 pomp

-0.23

ilateral

-0.23

POSITIVE LOGITS

æ²Ļ

0.29

dess

0.27

 sand

0.26

è§ģ

0.25

ridor

0.25

ãģ¾ãģĹãģŁ

0.25

rip

0.25

vox

0.25

vox

0.25

iram

0.25

Activations Density 0.078%

a

No Comments

No Known Activations