INDEX

Explanations

code/text snippets

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

peace

-0.27

 peace

-0.27

 primitive

-0.26

å®Įæķ´æĢ§

-0.25

itone

-0.25

æĺ¥èĬĤ

-0.25

 sanity

-0.25

ç¡Ĳ

-0.25

 legis

-0.25

.tk

-0.25

POSITIVE LOGITS

/en

0.26

æ·¹æ²¡

0.26

—you

0.25

otts

0.24

è¨ĩ

0.24

åıĪæľī

0.24

èĥ½å¤Łåľ¨

0.24

¹Ħ

0.24

åĳ½è¿Ĳ

0.24

—and

0.24

Activations Density 41.990%

code/text snippets

No Comments

No Known Activations