INDEX

Explanations

hipp

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

à¸ĸà¸²

-0.25

UPS

-0.24

_modal

-0.24

ocalypse

-0.24

vig

-0.24

ghi

-0.23

çĸ

-0.23

inci

-0.23

vig

-0.23

uros

-0.23

POSITIVE LOGITS

 Boeh

0.27

åĵ²

0.27

lab

0.26

pt

0.26

å±¿

0.24

Blog

0.24

arch

0.24

á»ıi

0.23

mitt

0.23

æĿ¾å¼Ľ

0.23

Activations Density 0.224%

hipp

No Comments

No Known Activations