INDEX

Explanations

qualifiers and opinions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

umni

-0.30

mesh

-0.28

encers

-0.27

æĸ¹

-0.26

tan

-0.26

å¤Ħ

-0.25

 sheds

-0.25

ialis

-0.25

oth

-0.25

olang

-0.24

POSITIVE LOGITS

andle

0.29

 Nimbus

0.26

çĢĳ

0.25

 unint

0.24

enant

0.24

ä¸ĭåįĬ

0.24

 cuff

0.24

çħ§é¡§

0.23

vfs

0.23

èĴŁ

0.23

Activations Density 0.002%

qualifiers and opinions

No Comments

No Known Activations