INDEX

Explanations

Code/programming-related writing

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

opies

-0.31

ila

-0.29

-dismiss

-0.29

.php

-0.27

çĲĨ

-0.27

 æķ

-0.26

Dismiss

-0.25

è°·

-0.25

åĵ²åŃ¦

-0.25

åıĸ

-0.24

POSITIVE LOGITS

 Erick

0.28

KER

0.28

 Brewer

0.27

çĸĶ

0.26

æºĥ

0.25

kov

0.24

æĺ¯éŁ©åĽ½

0.24

Pot

0.24

é©¬ä¸ģ

0.24

æ»¡èĦ¸

0.23

Activations Density 0.052%

Code/programming-related writing

No Comments

No Known Activations