INDEX

Explanations

objectivity

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

æĺ¯ä¸įåı¯èĥ½

-0.26

APPER

-0.26

soon

-0.25

itage

-0.25

ishing

-0.25

åħĪæĺ¯

-0.24

åŃĺæ´»

-0.23

icha

-0.23

ptions

-0.23

ies

-0.23

POSITIVE LOGITS

 scientific

0.28

æĢ§åĴĮ

0.27

cad

0.27

 panc

0.25

 enough

0.25

 Appro

0.25

ç®¡çĲĨåĴĮ

0.25

 ness

0.25

ness

0.25

dec

0.25

Activations Density 0.011%

objectivity

No Comments

No Known Activations