INDEX

Explanations

pharmacokinetics

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

ãĥĩãĤ£ãĥ³ãĤ°

-0.28

reas

-0.28

æ´»åĬ¨ä¸Ń

-0.27

 TripAdvisor

-0.26

bsites

-0.24

Ð¸ÑĢÑĥÐµÐ¼

-0.24

 rehab

-0.24

ç»ĦåĽ¾

-0.24

zheimer

-0.23

 Activities

-0.23

POSITIVE LOGITS

achs

0.27

å¿ħè¦ģ

0.26

olls

0.25

syntax

0.25

Ð»ÐµÐºÑĤ

0.25

è®º

0.24

 nett

0.24

overs

0.24

Lol

0.24

 Dillon

0.24

Activations Density 0.025%

pharmacokinetics

No Comments

No Known Activations