INDEX

Explanations

Scientific/chemical contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 amnesty

-0.29

Visited

-0.26

 miá»ħn

-0.26

transforms

-0.26

_eng

-0.25

Geom

-0.25

åħį

-0.25

çļĦçľ¼ç¥ŀ

-0.25

ä»ĺ

-0.24

è²Į

-0.24

POSITIVE LOGITS

æĬĺ

0.27

 targetType

0.27

ifa

0.27

reta

0.26

tir

0.26

ÑĪÐ¸Ð²

0.25

 Poly

0.24

çĽ´éĢļè½¦

0.24

 retreat

0.23

 shallow

0.23

Activations Density 0.005%

Scientific/chemical contexts

No Comments

No Known Activations