INDEX

Explanations

ard

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

uers

-0.28

è¶³

-0.27

æĿ¡

-0.26

intel

-0.25

ç´§

-0.25

ä¸ĢæĿ¡

-0.25

 interests

-0.25

 registr

-0.24

LS

-0.24

 politics

-0.24

POSITIVE LOGITS

edException

0.32

æŁĲäºĽ

0.28

.GetInstance

0.27

æ¯ĸ

0.26

acht

0.26

 Newest

0.25

oran

0.25

(Collections

0.24

æ£ł

0.24

 CONS

0.24

Activations Density 0.001%

ard

No Comments

No Known Activations