INDEX

Explanations

IT support/forum context

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

åŃ¦

-0.26

 Cross

-0.26

tec

-0.25

çº¤

-0.25

undler

-0.25

å¡«åħħ

-0.24

åĬ¨çĶŁæĪĲ

-0.24

 Perkins

-0.24

åŃ¸

-0.24

prim

-0.24

POSITIVE LOGITS

å¹³åı°

0.31

rated

0.30

 platforms

0.30

æŃ¢

0.28

ceu

0.28

plat

0.27

 platform

0.27

å¹³åı°ä¸Ĭ

0.26

inality

0.26

cli

0.25

Activations Density 0.005%

IT support/forum context

No Comments

No Known Activations