INDEX

Explanations

for

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

ouch

-0.28

cue

-0.27

åĳ¸

-0.25

èµĥ

-0.24

/db

-0.24

iti

-0.24

ï»¿↵

-0.24

å¤ļæĸ¹

-0.24

Toe

-0.24

åĪĨåĮĸ

-0.24

POSITIVE LOGITS

à¸¬

0.28

velocity

0.26

ãĥĵãĥ«

0.26

å¤Ħåľ¨

0.25

æĶ¶éĽĨ

0.25

office

0.24

strip

0.24

èį¡

0.24

 handlers

0.24

 retro

0.24

Activations Density 0.028%

for

No Comments

No Known Activations