INDEX

Explanations

Mahm

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

 pend

-0.26

 ascend

-0.26

èĬĻèĵī

-0.25

Rug

-0.25

raise

-0.25

 correspond

-0.24

Ã©l

-0.24

conc

-0.24

tra

-0.24

 frank

-0.24

POSITIVE LOGITS

rots

0.26

ients

0.24

 Pussy

0.24

å£ŀ

0.24

éĿĻçĶµ

0.24

.HttpServletResponse

0.23

ENSE

0.23

éĢĢå½¹

0.23

ÑģÑĤÑĢÐ°Ð¸Ð²Ð°

0.23

.SpringBootTest

0.23

Activations Density 0.007%

Mahm

No Comments

No Known Activations