INDEX

Explanations

enic

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

å¯Ĩåº¦

-0.27

ÙĤØ¯

-0.27

uto

-0.25

ungan

-0.25

edor

-0.24

 strategist

-0.24

 adel

-0.23

à¹Ĥà¸ģ

-0.23

 density

-0.23

woord

-0.23

POSITIVE LOGITS

 Track

0.32

è¿ĻåĿĹ

0.29

åħ¶æ¬¡

0.26

Track

0.25

åĩºäºĨ

0.25

lical

0.25

kel

0.24

argar

0.24

JNIEnv

0.24

Tracker

0.24

Activations Density 3.673%

enic

No Comments

No Known Activations