INDEX

Explanations

software development

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

ivalent

-0.28

éŃĶé¬¼

-0.27

ocale

-0.26

âľ²

-0.26

æļĹ

-0.26

è¸©

-0.26

çº¶

-0.25

èĢĮä¸į

-0.25

éĻĩ

-0.25

ä¸¤å¤©

-0.25

POSITIVE LOGITS

eras

0.29

_intersection

0.28

äº¤

0.27

:checked

0.27

.Globalization

0.27

 intersect

0.27

age

0.27

-turn

0.26

 intersection

0.25

 turn

0.25

Activations Density 0.015%

software development

No Comments

No Known Activations