INDEX

Explanations

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

 espec

-0.25

ç²ķ

-0.25

å°ī

-0.25

 Moody

-0.25

è¿Ļä»½

-0.25

éĢĤ

-0.25

Nom

-0.25

æ·±æ·±

-0.24

ervas

-0.24

-opacity

-0.24

POSITIVE LOGITS

cele

0.25

sch

0.25

ray

0.25

 staying

0.25

 denen

0.24

ªĮ

0.24

list

0.24

arged

0.24

nx

0.23

cxx

0.23

Activations Density 42.276%

code

No Comments

No Known Activations