INDEX

Explanations

patent descriptions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 following

-0.29

pro

-0.25

hton

-0.25

ambique

-0.25

 drive

-0.25

ensen

-0.25

uba

-0.24

HING

-0.24

antz

-0.24

 there

-0.24

POSITIVE LOGITS

 onCreate

0.30

 Repeat

0.26

scr

0.26

repeat

0.25

 NavParams

0.25

ETA

0.24

ä¿®å»º

0.24

umd

0.24

Repeat

0.24

onClick

0.24

Activations Density 0.002%

patent descriptions

No Comments

No Known Activations