INDEX

Explanations

technical reports/code

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

 concept

-0.27

éĢĤåº¦

-0.26

Ł

-0.26

(Scene

-0.25

stem

-0.25

éĢĤ

-0.25

åĩº

-0.25

 algebra

-0.25

concept

-0.24

POSITIVE LOGITS

çĦĵ

0.26

imap

0.26

çĸĳéļ¾

0.25

ê²Ģ

0.24

é¡½

0.24

Pacific

0.24

ä¸ļåĬ¡

0.23

_FAULT

0.23

åħĪå¯¼

0.23

/arm

0.23

Activations Density 3.905%

technical reports/code

No Comments

No Known Activations